← Back to history

Pipeline run

fc3d1b12-2b6c-4d63-bcec-f2574b117d97

Pipeline LLM cost (USD)
API 1: $0.0078 API 2: $0.0001 API 3: $0.0000 Total: $0.0080

Client output enrichment

v2 Skill cluster · Nature of work · AI index · Tech stack maturity · Evidence · KRA description
SPARSE JD sources · ai_index: jd · nature_of_work: jd · tech_stack_maturity: jd
Nature of work · Master Data Management
Co-design MDM information architecture, configure Informatica match/merge rules, and steer releases, live-service fixes, and delivery quality against the roadmap. Also manage and upskill the team while enforcing data governance, security, and technical standards.
"• Ability to shape master data management strategy"
Tech stack maturity
Mainstream Legacy
The combination of DevOps with Informatica suggests a mostly established enterprise data-integration environment built around mainstream, on-prem or hybrid tooling rather than a cloud-native or bleeding-edge stack.
AI index (0 = no AI use, 5 = totally AI-dependent · v2.1)
0.20 / 5
· Title match
Has AI skill
· AI skill (primary)
· AI skill (secondary)
· On AI team
· Builds AI products
vocab breakdown (legacy)
Assistants (×1):
Frameworks (×2):
Models / concepts (×3): embeddings, AI
Evidence — skills matched in JD (4)
Informatica DevOps Master Data Management Data Governance
Skill cluster (2 dimension groups, role-scoped)
CI/CD Pipeline Platforms
DevOps
Cross-cutting / unaligned
Informatica Master Data Management Data Governance
Show KRA description ↓
• Ability to co-design the information architecture for different MDM solutions • Guide on the development and delivery of a series of major and minor releases through the year as specified by the roadmap • Ensure the performance, quality and fit for market needs of the MDM output • Work collaboratively with the wider team to ensure on-time and in-full delivery • Configuring the MDM match and merge rules • Manage the wider development team • Assist in upskilling team members on Informatica solution • Work with the DevOps team on issues relating to the live service • Monitor third-party delivery quality to ensure it meets with Unilever standards. • Review and enhance the technical standards of the implementation • Ensure information security and personal information policies are abided and always front of mind for the wider development team • Ability to shape master data management strategy • Data governance

Signals

Skill data-engineer
0.25
Alias data-analyst
1.00
KRA engineering-manager
0.52

Post-classification

Centroidupdated · n=8
Alias collision log
New-role queue
New skills captured2
New KRA capturedyes

Captured for admin review

Master Data Management primary Data Governance Engineer pending
Data Governance primary Data Governance Engineer pending
R&R fragment (sim 0.00) Data Governance Engineer pending

• Ability to co-design the information architecture for different MDM solutions • Guide on the development and delivery of a series of major and minor releases through the year as specified by the roa…

Status: completed Created: 2026-05-27T16:12:52.844240Z Updated: 2026-05-27T16:13:48.439380Z API 3 duration: 9328 ms
Flow Current 3-step pipeline

1 POST /skills/extract-from-jd

2 POST /skills/extract-details

3 POST /skills/final-role-output

Role Chosen role & resolution

Data Governance Engineer

domain · Data Engineering & Analytics CASE DOMAIN

slug: data-governance-engineer · id: 146 · source: db

Domain=Data Engineering & Analytics; The JD centers on master data management, data governance, information architecture, match-and-merge rules, and MDM solution oversight, which best aligns with Data Governance Engineer.

Matched skills

Master Data ManagementMDMinformation architectureMDM match and merge rulesInformaticaDevOpsinformation securitypersonal information policiesdata governance

Matched dimensions

Master Data Management strategyInformation architecture designData governanceRelease and delivery managementTechnical standards and implementation qualitySecurity and privacy complianceTeam leadership and enablementOperational support for live services

Matched KRAs

co-design the information architecturedeliver major and minor releasesensure performance, quality and fit for market needsconfiguring the MDM match and merge rulesmanage the wider development teamupskill team members on Informatica solutionwork with the DevOps team on issues relating to the live servicereview and enhance the technical standards of the implementationensure information security and personal information policies are abided

Resolution: in_db — role exists in library; skill↔dim and role↔dim links saved when applicable.

0
New skills
0
Skill↔dim saved
0
Role↔dim saved
0
Skipped

Job description

• Join a business empowering people with data & technology|Be part of and exciting and evolving Data & Analytics journey



About Our Client

For Unilever to remain ruthless in the future, the business needs to continue the path to become data intelligent. The Data & Insights team will persevere to make Unilever Data Intelligent, powering key resolutions with data, insights, advanced analytics, and AI. Our goal is to enable democratization of data, information and insights as a completely agile organization that builds fantastic careers for our people and is accountable for delivering great work that maximizes impact and delivers growth.

This Data & Analytics function endeavours to create clear accountabilities for all aspects of Data Strategy, Data Management, Information Management, Analytics, and Insights. We would be accountable for impact of solutions, maintaining market relevance and minimising unnecessary overlaps in analytics products, ensuring simplicity and that our solutions better meet the needs of our users. We would partner with the Digital and Data Legal Counsel to ensure that our Data Defence (Privacy, Governance, Quality, etc) is well structured and sufficiently robust to use data and AI correctly throughout the enterprise. We would democratize information across the business, while supporting the culture shift required for data carrying resolution making.

Further, this team would drive capacity unlock from manual and duplicative reporting capabilities, while also refocusing a portion of the unlock on embedding predictive and prescriptive analytics capabilities into our highest potential opportunities. We have four key operating postulates:
• One team
• Connected to the business
• Deploying with pace and discipline
• Designing for experience


Job Description

Key Responsibilities:
• Ability to co-design the information architecture for different MDM solutions
• Guide on the development and delivery of a series of major and minor releases through the year as specified by the roadmap
• Ensure the performance, quality and fit for market needs of the MDM output
• Work collaboratively with the wider team to ensure on-time and in-full delivery
• Configuring the MDM match and merge rules
• Manage the wider development team
• Assist in upskilling team members on Informatica solution
• Work with the DevOps team on issues relating to the live service
• Monitor third-party delivery quality to ensure it meets with Unilever standards.
• Review and enhance the technical standards of the implementation
• Ensure information security and personal information policies are abided and always front of mind for the wider development team
• Ability to shape master data management strategy
• Data governance


The Successful Applicant

Experience and qualifications required:

Essential:
• Strong working knowledge of Informatica MDM tool
• Proven success in roles guiding design and configuration of MDM implementations
• Demonstrated ability to work with upstream and downstream elements impacting and being impacted by the application
• Ability to explain technical aspects to business users and helping them refine requirements as needed
• Experience performing root cause analysis and resolution of issues
• Ability to work both unaccompanied and collaboratively to resolve issues
• Prior experience working with Informatica cloud offerings, including Informatica C360
• Experience of Agile/DevOps development lifecycle from conception to delivery.
• Technical knowledge on Cloud based data and analytics tools and technologies, specifically Azure, Data Lake Store, Azure Data Factory, Azure Databricks
• Experience of working with and managing supplier teams/resources.
• Excellent verbal, written and interpersonal communication skills.
• Possesses good analytical thinking to develop solutions and propose action plans
• Ability to learn new tools, technologies, and process quickly
• Self-motivated problem solver; able to thrive in a dynamic and result-carrying environment
• Thorough understanding of applicable standards and procedures including technical, quality, safety, and financial matters across all areas of delivery


Desirable:

Prior development/design experience on IDQ Informatica module

Professional certification (Agile methodologies, PMI, ITIL, etc.)

Domain expertise in Analytics and Data Lake Platform & Technologies  Experience of working within consumer goods or retail industry. Key Interfaces:

Internal
• Data SMEs, Business Data Lake Factory, Unilever data lake, Cloud platform (landscape) team, Technical Design Authority, other UniOps teams.
• Data & Analytics Management team. External Third-party resources working within Data Lake delivery.


Standards of Management
• Passion for High Performance (Inspires the energy needed to win and grow)
• Keen to continuously learn
• Agility (constantly curious & daring)


What's On Offer

What do we offer:

From our foundation, Unilever has been a purpose-driven company. Today, our purpose is to make sustainable living commonplace. We are working to create a brighter future every day with brands and services that help people feel good, look good and get more out of life. That includes us - the people who work for Unilever, as well as the world around us. Unilever's flexible rewards and benefits are designed to help us all have sustainable households, for whatever life stage you are now and in the future. These include:
• Great work environment
• Flexible work environment built on trust and freedom
• Pension scheme
• Employee Assistance Program for you and your family
• Well-being hub with access to benefits such as Healthcare, eye tests, health checks, occupational physio


Whilst the role is advertised on a full-time basis, we would be happy to discuss possible flexible working options and what this may look like for you. We are a key advocate of well-being and offer a variety of support for our people including hubs, programs, and development opportunities. We strive to achieve a family-friendly and inclusive workplace and to, above all, create possibilities for all. And last but certainly not least - the chance to be a part of a dynamic team with the backing of the globally renowned Unilever brand. Our commitment to Equality, Diversity & Inclusion: Diversity at Unilever is about inclusion, embracing differences, creating possibilities, and growing together for better business performance. We embrace diversity in our workforce. This means giving full and fair consideration to all applicants and continuing the development of all employees regardless of age, disability, gender reassignment, race, religion or belief, gender, sexual orientation, marriage and civil partnership, and pregnancy and maternity.

Contact: UnileverSanya Seth

Quote job ref: JN-022023-5935615

Skills from this JD

Each row merges API 1 extraction, API 2 library match / v3 orchestration (dimensions + locked dims), and API 3 persistence tags.

Informatica Primary Library skill API 3: existing canonical (in_db) Existing skill (matched library)
Canonical: Informatica id=117 · informatica

Aliases — catalog

  • Informatica (CANONICAL) primary

Context tags (catalog)

CDC Cloud Data Integration ELT ETL IICS PowerCenter data integration data quality data warehousing lookup transformation mapping repository session source qualifier workflow

Stored enrichment (catalog DB)

Category
Platform
Sub-category
Data Integration Platform
Vendor
Informatica
License
proprietary
Year introduced
1993
Confidence
0.90
Version strategy
NOT_APPLICABLE

Maturity reasoning: Informatica appears frequently in enterprise data-integration and ETL job postings, especially alongside cloud migration and MDM roles; it remains a common hiring keyword rather than a sunset technology.

Skill profile (library / DB)

Skill nature
PLATFORM
Volatility
STABLE
Typical lifespan
EVERGREEN
Category id
9
Sub-category id
114
Extractable
True
Also category
False

Dimensions (API 2 worklist)

  • ETL and ELT Tooling Catalog dimension db id 24

    Library dimension (catalog)

    Roles linked in library: Data Engineer

API 3 link attempts (this skill)

Dimension Skill↔dim Role↔dim Outcome
ETL and ELT Tooling
etl-and-elt-tooling
Existing dimension (library) · Role↔dimension skipped (dimension not under chosen role)
DevOps Primary Library skill API 3: existing canonical (in_db) Existing skill (matched library)
Canonical: DevOps id=1216 · devops

Aliases — catalog

  • DevOps (CANONICAL)

Context tags (catalog)

Agile Ansible Automation CI/CD Cloud-native Continuous Deployment Continuous Integration Docker GitOps Infrastructure as Code Jenkins Kubernetes Microservices Monitoring SRE Terraform

Stored enrichment (catalog DB)

Category
Methodology
Sub-category
Devops Methodology
Confidence
0.97
Version strategy
NOT_APPLICABLE

Maturity reasoning: DevOps appears in a large share of software and platform engineering job descriptions, often alongside CI/CD, Kubernetes, and cloud tooling; it is a standard hiring-pipeline keyword rather than a niche specialty.

Skill profile (library / DB)

Skill nature
METHODOLOGY
Volatility
STABLE
Typical lifespan
EVERGREEN
Category id
8
Sub-category id
922
Extractable
True
Also category
False

Dimensions (API 2 worklist)

  • CI/CD Pipeline Platforms Catalog dimension db id 150

    Library dimension (catalog)

    Roles linked in library: DevOps Engineer

  • Deployment and Release Patterns Catalog dimension db id 140

    Library dimension (catalog)

    Roles linked in library: Cloud Architect

  • Infrastructure as Code Catalog dimension db id 132

    Library dimension (catalog)

    Roles linked in library: Cloud Architect, DevOps Engineer

API 3 link attempts (this skill)

Dimension Skill↔dim Role↔dim Outcome
CI/CD Pipeline Platforms
ci-cd-pipeline-platforms
Existing dimension (library) · Role↔dimension skipped (dimension not under chosen role)
Deployment and Release Patterns
deployment-and-release-patterns
Existing dimension (library) · Role↔dimension skipped (dimension not under chosen role)
Infrastructure as Code
infrastructure-as-code
Existing dimension (library) · Role↔dimension skipped (dimension not under chosen role)
Master Data Management Primary New / orchestrated API 3: new canonical path (new) New / unmatched skill (orchestrated in API 2)

Skill enrichment (orchestrator / LLM)

No Stage 7 enrichment blob on this skill (orchestrator skipped enrichment).

Derived legacy fields
Category
Data Governance
Sub-category
general
Skill nature
CONCEPT
Volatility
MEDIUM
Typical lifespan
MULTI_YEAR
Version strategy
UNVERSIONED
Data Governance Primary New / orchestrated API 3: new canonical path (new) New / unmatched skill (orchestrated in API 2)

Skill enrichment (orchestrator / LLM)

No Stage 7 enrichment blob on this skill (orchestrator skipped enrichment).

Derived legacy fields
Category
Data Governance
Sub-category
general
Skill nature
CONCEPT
Volatility
MEDIUM
Typical lifespan
MULTI_YEAR
Version strategy
UNVERSIONED

All API 3 persistence rows

Same grid as the skill-extractor “Persistence items” table: one row per (skill × dimension) work item.

Skill Tag Dimension Skill↔dim Role↔dim Outcome Notes
Informatica in_db
ETL and ELT Tooling
etl-and-elt-tooling
Existing dimension (library) · Role↔dimension skipped (dimension not under chosen role)
DevOps in_db
CI/CD Pipeline Platforms
ci-cd-pipeline-platforms
Existing dimension (library) · Role↔dimension skipped (dimension not under chosen role)
DevOps in_db
Deployment and Release Patterns
deployment-and-release-patterns
Existing dimension (library) · Role↔dimension skipped (dimension not under chosen role)
DevOps in_db
Infrastructure as Code
infrastructure-as-code
Existing dimension (library) · Role↔dimension skipped (dimension not under chosen role)

Library artifacts (this run)

Kind Detail DB id
canonical_skill_proposed Master Data Management | type=Data Governance subtype=general nature=CONCEPT lifespan=MULTI_YEAR
canonical_skill_proposed Data Governance | type=Data Governance subtype=general nature=CONCEPT lifespan=MULTI_YEAR
nano JD Parser — gpt-4.1-nano click to toggle
RoleMaster Data Management (MDM) Specialist
CompanyUnilever
ExperienceProven success in roles guiding design and configuration of MDM implementations
DomainConsumer Packaged Goods
JD type pass

Certifications

Agile methodologies PMI ITIL
Show raw JSON
{
  "JD_type": "pass",
  "about_company": {
    "source_marker": {
      "first_5_words": "For Unilever to remain ruthless",
      "last_5_words": "maximizes impact and delivers growth."
    },
    "text": "For Unilever to remain ruthless in the future, the business needs to continue the path to become data intelligent. The Data \u0026 Insights team will persevere to make Unilever Data Intelligent, powering key resolutions with data, insights, advanced analytics, and AI. Our goal is to enable democratization of data, information and insights as a completely agile organization that builds fantastic careers for our people and is accountable for delivering great work that maximizes impact and delivers growth.",
    "word_count": 64
  },
  "archetype_override_applied": true,
  "archetype_override_matched_skills": [
    "Informatica",
    "Agile",
    "Make",
    "DevOps",
    "Databricks",
    "Analytics",
    "Azure",
    "Cloud",
    "Role",
    "roles",
    "policies",
    "health checks",
    "root cause analysis"
  ],
  "certifications": [
    "Agile methodologies",
    "PMI",
    "ITIL"
  ],
  "company_name": "Unilever",
  "ctc": null,
  "domain": {
    "primary": {
      "aliases": [
        "CPG",
        "Retail"
      ],
      "domain": "Consumer Packaged Goods"
    },
    "secondary": null
  },
  "education": [],
  "experience": {
    "max": null,
    "min": 5,
    "raw": "Proven success in roles guiding design and configuration of MDM implementations"
  },
  "job_locations": [],
  "role": "Master Data Management (MDM) Specialist",
  "role_aliases": [
    "MDM Consultant",
    "Data Management Specialist",
    "Data Analyst"
  ],
  "role_archetype": "Engineering",
  "roles_and_responsibilities": [
    {
      "bullet_count": 13,
      "heading": "Key Responsibilities",
      "heading_was_present": true,
      "source_marker": {
        "first_5_words": "\u2022 Ability to co-design the",
        "last_5_words": "and personal information policies are"
      },
      "text": "\u2022 Ability to co-design the information architecture for different MDM solutions\n\u2022 Guide on the development and delivery of a series of major and minor releases through the year as specified by the roadmap\n\u2022 Ensure the performance, quality and fit for market needs of the MDM output\n\u2022 Work collaboratively with the wider team to ensure on-time and in-full delivery\n\u2022 Configuring the MDM match and merge rules\n\u2022 Manage the wider development team\n\u2022 Assist in upskilling team members on Informatica solution\n\u2022 Work with the DevOps team on issues relating to the live service\n\u2022 Monitor third-party delivery quality to ensure it meets with Unilever standards.\n\u2022 Review and enhance the technical standards of the implementation\n\u2022 Ensure information security and personal information policies are abided and always front of mind for the wider development team\n\u2022 Ability to shape master data management strategy\n\u2022 Data governance",
      "word_count": 139
    }
  ],
  "urls": []
}
API 1 — extract-from-jd click to toggle
{
  "final_skills": [
    {
      "is_primary": true,
      "skill_name": "Informatica"
    },
    {
      "is_primary": true,
      "skill_name": "DevOps"
    },
    {
      "is_primary": true,
      "skill_name": "Master Data Management"
    },
    {
      "is_primary": true,
      "skill_name": "Data Governance"
    }
  ],
  "jd_role": {
    "display_name": "Master Data Management (MDM) Specialist",
    "rationale": null,
    "role_aliases": [
      "MDM Consultant",
      "Data Management Specialist",
      "Data Analyst"
    ],
    "role_archetype": "Engineering",
    "slug": ""
  },
  "nano_parsed": {
    "JD_type": "pass",
    "about_company": {
      "source_marker": {
        "first_5_words": "For Unilever to remain ruthless",
        "last_5_words": "maximizes impact and delivers growth."
      },
      "text": "For Unilever to remain ruthless in the future, the business needs to continue the path to become data intelligent. The Data \u0026 Insights team will persevere to make Unilever Data Intelligent, powering key resolutions with data, insights, advanced analytics, and AI. Our goal is to enable democratization of data, information and insights as a completely agile organization that builds fantastic careers for our people and is accountable for delivering great work that maximizes impact and delivers growth.",
      "word_count": 64
    },
    "archetype_override_applied": true,
    "archetype_override_matched_skills": [
      "Informatica",
      "Agile",
      "Make",
      "DevOps",
      "Databricks",
      "Analytics",
      "Azure",
      "Cloud",
      "Role",
      "roles",
      "policies",
      "health checks",
      "root cause analysis"
    ],
    "certifications": [
      "Agile methodologies",
      "PMI",
      "ITIL"
    ],
    "company_name": "Unilever",
    "ctc": null,
    "domain": {
      "primary": {
        "aliases": [
          "CPG",
          "Retail"
        ],
        "domain": "Consumer Packaged Goods"
      },
      "secondary": null
    },
    "education": [],
    "experience": {
      "max": null,
      "min": 5,
      "raw": "Proven success in roles guiding design and configuration of MDM implementations"
    },
    "job_locations": [],
    "role": "Master Data Management (MDM) Specialist",
    "role_aliases": [
      "MDM Consultant",
      "Data Management Specialist",
      "Data Analyst"
    ],
    "role_archetype": "Engineering",
    "roles_and_responsibilities": [
      {
        "bullet_count": 13,
        "heading": "Key Responsibilities",
        "heading_was_present": true,
        "source_marker": {
          "first_5_words": "\u2022 Ability to co-design the",
          "last_5_words": "and personal information policies are"
        },
        "text": "\u2022 Ability to co-design the information architecture for different MDM solutions\n\u2022 Guide on the development and delivery of a series of major and minor releases through the year as specified by the roadmap\n\u2022 Ensure the performance, quality and fit for market needs of the MDM output\n\u2022 Work collaboratively with the wider team to ensure on-time and in-full delivery\n\u2022 Configuring the MDM match and merge rules\n\u2022 Manage the wider development team\n\u2022 Assist in upskilling team members on Informatica solution\n\u2022 Work with the DevOps team on issues relating to the live service\n\u2022 Monitor third-party delivery quality to ensure it meets with Unilever standards.\n\u2022 Review and enhance the technical standards of the implementation\n\u2022 Ensure information security and personal information policies are abided and always front of mind for the wider development team\n\u2022 Ability to shape master data management strategy\n\u2022 Data governance",
        "word_count": 139
      }
    ],
    "urls": []
  },
  "rejected": false,
  "rejection_reason": null,
  "run_id": "fc3d1b12-2b6c-4d63-bcec-f2574b117d97",
  "stage3_signals": {
    "alias_found": true,
    "alias_match_roles": [
      {
        "display_name": "Data Analyst",
        "kra_matches": null,
        "matched_count": null,
        "matched_skills": null,
        "role_id": 143,
        "score": 1.0,
        "slug": "data-analyst",
        "total_count": null
      }
    ],
    "kra_match_roles": [
      {
        "display_name": "Engineering Manager",
        "kra_matches": [
          {
            "kra_text": "Set team goals and delivery plans",
            "sentence": "Work collaboratively with the wider team to ensure on-time and in-full delivery",
            "similarity": 0.6416
          },
          {
            "kra_text": "Set team goals and delivery plans",
            "sentence": "Guide on the development and delivery of a series of major and minor releases through the year as specified by the roadmap",
            "similarity": 0.4691
          },
          {
            "kra_text": "facilitate technical and delivery decisions",
            "sentence": "Review and enhance the technical standards of the implementation",
            "similarity": 0.4636
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 121,
        "score": 0.5248,
        "slug": "engineering-manager",
        "total_count": null
      },
      {
        "display_name": "Flutter Developer",
        "kra_matches": [
          {
            "kra_text": "collaborate with design, product, and backend teams",
            "sentence": "Work collaboratively with the wider team to ensure on-time and in-full delivery",
            "similarity": 0.5845
          },
          {
            "kra_text": "collaborate with design, product, and backend teams",
            "sentence": "Ability to co-design the information architecture for different MDM solutions",
            "similarity": 0.4827
          },
          {
            "kra_text": "collaborate with design, product, and backend teams",
            "sentence": "Work with the DevOps team on issues relating to the live service",
            "similarity": 0.4807
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 74,
        "score": 0.516,
        "slug": "flutter-developer",
        "total_count": null
      },
      {
        "display_name": "DevOps Engineer",
        "kra_matches": [
          {
            "kra_text": "Collaborates with development teams to improve build processes, reduce deployment friction, containerize applications, and adopt DevOps best practices.",
            "sentence": "Work with the DevOps team on issues relating to the live service",
            "similarity": 0.5616
          },
          {
            "kra_text": "Collaborates with development teams to improve build processes, reduce deployment friction, containerize applications, and adopt DevOps best practices.",
            "sentence": "Work collaboratively with the wider team to ensure on-time and in-full delivery",
            "similarity": 0.5134
          },
          {
            "kra_text": "Monitors CI/CD pipeline reliability, identifies bottlenecks in delivery workflows, and improves deployment frequency, lead time, and failure recovery rate.",
            "sentence": "Monitor third-party delivery quality to ensure it meets with Unilever standards.",
            "similarity": 0.4458
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 10,
        "score": 0.5069,
        "slug": "devops-engineer",
        "total_count": null
      },
      {
        "display_name": "Angular Frontend Developer",
        "kra_matches": [
          {
            "kra_text": "collaboration with design and QA",
            "sentence": "Work collaboratively with the wider team to ensure on-time and in-full delivery",
            "similarity": 0.5312
          },
          {
            "kra_text": "code review and refactoring",
            "sentence": "Review and enhance the technical standards of the implementation",
            "similarity": 0.4809
          },
          {
            "kra_text": "collaboration with design and QA",
            "sentence": "Ability to co-design the information architecture for different MDM solutions",
            "similarity": 0.4704
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 90,
        "score": 0.4942,
        "slug": "angular-frontend-developer",
        "total_count": null
      },
      {
        "display_name": "Data Engineer",
        "kra_matches": [
          {
            "kra_text": "Designs dimensional models, star schemas, data vault structures, and curated data mart tables to support BI tools and self-service analytics consumption.",
            "sentence": "Ability to shape master data management strategy",
            "similarity": 0.523
          },
          {
            "kra_text": "Designs dimensional models, star schemas, data vault structures, and curated data mart tables to support BI tools and self-service analytics consumption.",
            "sentence": "Ability to co-design the information architecture for different MDM solutions",
            "similarity": 0.5166
          },
          {
            "kra_text": "Monitors pipeline health, SLA breach alerts, and job failure notifications, and performs root cause analysis for data pipeline incidents.",
            "sentence": "Work with the DevOps team on issues relating to the live service",
            "similarity": 0.44
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 2,
        "score": 0.4932,
        "slug": "data-engineer",
        "total_count": null
      }
    ],
    "skill_match_roles": [
      {
        "display_name": "Data Engineer",
        "kra_matches": null,
        "matched_count": 1,
        "matched_skills": [
          "Informatica"
        ],
        "role_id": 2,
        "score": 0.25,
        "slug": "data-engineer",
        "total_count": 4
      },
      {
        "display_name": "Cloud Architect",
        "kra_matches": null,
        "matched_count": 1,
        "matched_skills": [
          "DevOps"
        ],
        "role_id": 9,
        "score": 0.25,
        "slug": "cloud-architect",
        "total_count": 4
      },
      {
        "display_name": "DevOps Engineer",
        "kra_matches": null,
        "matched_count": 1,
        "matched_skills": [
          "DevOps"
        ],
        "role_id": 10,
        "score": 0.25,
        "slug": "devops-engineer",
        "total_count": 4
      }
    ]
  },
  "stage4_decision": {
    "alias_collision_detected": false,
    "case": "DOMAIN",
    "chosen_role": {
      "display_name": "Data Governance Engineer",
      "kra_matches": null,
      "matched_count": null,
      "matched_skills": null,
      "role_id": 146,
      "score": 0.91,
      "slug": "data-governance-engineer",
      "total_count": null
    },
    "confidence": 0.91,
    "is_new_role": false,
    "llm2_fired": false,
    "llm2_reasoning": null,
    "matched_dimensions": [
      "Master Data Management strategy",
      "Information architecture design",
      "Data governance",
      "Release and delivery management",
      "Technical standards and implementation quality",
      "Security and privacy compliance",
      "Team leadership and enablement",
      "Operational support for live services"
    ],
    "matched_kras": [
      "co-design the information architecture",
      "deliver major and minor releases",
      "ensure performance, quality and fit for market needs",
      "configuring the MDM match and merge rules",
      "manage the wider development team",
      "upskill team members on Informatica solution",
      "work with the DevOps team on issues relating to the live service",
      "review and enhance the technical standards of the implementation",
      "ensure information security and personal information policies are abided"
    ],
    "matched_skills": [
      "Master Data Management",
      "MDM",
      "information architecture",
      "MDM match and merge rules",
      "Informatica",
      "DevOps",
      "information security",
      "personal information policies",
      "data governance"
    ],
    "new_role_display_name": null,
    "new_role_slug": null,
    "queued": false,
    "reasoning": "Domain=Data Engineering \u0026 Analytics; The JD centers on master data management, data governance, information architecture, match-and-merge rules, and MDM solution oversight, which best aligns with Data Governance Engineer.",
    "sub_role": null
  },
  "stage5_updates": {
    "centroid_n_after": 8,
    "centroid_updated": true,
    "collision_log_id": null,
    "new_kra_attached": {
      "best_kra_similarity": 0.0,
      "queue_id": 1386,
      "r_and_r_preview": "\u2022 Ability to co-design the information architecture for different MDM solutions\n\u2022 Guide on the development and delivery of a series of major and minor releases through the year as specified by the roa",
      "role_display_name": "Data Governance Engineer",
      "role_slug": "data-governance-engineer",
      "status": "pending"
    },
    "new_skills_attached": [
      {
        "is_primary": true,
        "queue_id": 19009,
        "role_display_name": "Data Governance Engineer",
        "role_slug": "data-governance-engineer",
        "skill_name": "Master Data Management",
        "status": "pending"
      },
      {
        "is_primary": true,
        "queue_id": 19010,
        "role_display_name": "Data Governance Engineer",
        "role_slug": "data-governance-engineer",
        "skill_name": "Data Governance",
        "status": "pending"
      }
    ],
    "queue_entry_id": null,
    "v3_pipeline_triggered": false,
    "v3_role_slug": null,
    "v3_run_id": null
  }
}
API 2 — extract-details
{
  "alias_matches": [
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 311,
      "existing_alias_text": "Informatica",
      "input_term": "Informatica",
      "matched_canonical": {
        "category_id": 9,
        "display_name": "Informatica",
        "id": 117,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "PLATFORM",
        "slug": "informatica",
        "sub_category_id": 114,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    },
    {
      "alias_persist_skipped_reason": "alias_text already exists for this canonical skill",
      "alias_persisted": false,
      "existing_alias_id": 1852,
      "existing_alias_text": "DevOps",
      "input_term": "DevOps",
      "matched_canonical": {
        "category_id": 8,
        "display_name": "DevOps",
        "id": 1216,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "METHODOLOGY",
        "slug": "devops",
        "sub_category_id": 922,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "matched_via": "alias"
    }
  ],
  "candidate_roles": [
    {
      "display_name": "Data Engineer",
      "id": 2,
      "rationale": null,
      "role_archetype": null,
      "slug": "data-engineer",
      "source": "db"
    },
    {
      "display_name": "DevOps Engineer",
      "id": 10,
      "rationale": null,
      "role_archetype": null,
      "slug": "devops-engineer",
      "source": "db"
    },
    {
      "display_name": "Cloud Architect",
      "id": 9,
      "rationale": null,
      "role_archetype": null,
      "slug": "cloud-architect",
      "source": "db"
    }
  ],
  "chosen_role": {
    "display_name": "Data Governance Engineer",
    "id": 146,
    "rationale": "Domain=Data Engineering \u0026 Analytics; The JD centers on master data management, data governance, information architecture, match-and-merge rules, and MDM solution oversight, which best aligns with Data Governance Engineer.",
    "role_archetype": null,
    "slug": "data-governance-engineer",
    "source": "db"
  },
  "dimensions": [
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "ETL and ELT Tooling",
        "id": 24,
        "rationale": "Packaged tools for extracting, loading, and transforming data across systems. This dimension covers connector-based ingestion, transformation frameworks, and managed integration products.",
        "slug": "etl-and-elt-tooling",
        "source": "db"
      },
      "input_skill": "Informatica",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Data Engineer",
          "id": 2,
          "rationale": null,
          "role_archetype": null,
          "slug": "data-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "CI/CD Pipeline Platforms",
        "id": 150,
        "rationale": "Systems used to define, run, and maintain automated build and deployment workflows. This cluster is coherent because the role owns delivery automation end to end, including pipeline reliability and promotion logic.",
        "slug": "ci-cd-pipeline-platforms",
        "source": "db"
      },
      "input_skill": "DevOps",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "DevOps Engineer",
          "id": 10,
          "rationale": null,
          "role_archetype": null,
          "slug": "devops-engineer",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Deployment and Release Patterns",
        "id": 140,
        "rationale": "Patterns for promoting changes safely across environments, including rollout, rollback, and release gating strategies. Cloud Architects define these patterns so teams can deploy consistently across the platform.",
        "slug": "deployment-and-release-patterns",
        "source": "db"
      },
      "input_skill": "DevOps",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Cloud Architect",
          "id": 9,
          "rationale": null,
          "role_archetype": null,
          "slug": "cloud-architect",
          "source": "db"
        }
      ]
    },
    {
      "dimension": {
        "difficulty_hint": "well_known",
        "display_name": "Infrastructure as Code",
        "id": 132,
        "rationale": "Declarative provisioning and environment definition tools used to codify cloud infrastructure, repeatable environments, and platform standards. Cloud Architects use these to express reference architectures and guardrails.",
        "slug": "infrastructure-as-code",
        "source": "db"
      },
      "input_skill": "DevOps",
      "llm_role": null,
      "roles_from_db": [
        {
          "display_name": "Cloud Architect",
          "id": 9,
          "rationale": null,
          "role_archetype": null,
          "slug": "cloud-architect",
          "source": "db"
        },
        {
          "display_name": "DevOps Engineer",
          "id": 10,
          "rationale": null,
          "role_archetype": null,
          "slug": "devops-engineer",
          "source": "db"
        }
      ]
    }
  ],
  "input_final_skills": [
    "Informatica",
    "DevOps",
    "Master Data Management",
    "Data Governance"
  ],
  "input_llm_skills": [
    "Informatica",
    "DevOps",
    "Master Data Management",
    "Data Governance"
  ],
  "new_aliases_persisted": 0,
  "run_id": "fc3d1b12-2b6c-4d63-bcec-f2574b117d97",
  "skills_detail": [
    {
      "aliases_in_db": [
        {
          "alias_text": "Informatica",
          "alias_type": "CANONICAL",
          "id": 311,
          "is_primary": true,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 9,
        "display_name": "Informatica",
        "id": 117,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "PLATFORM",
        "slug": "informatica",
        "sub_category_id": 114,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "ETL and ELT Tooling",
            "id": 24,
            "rationale": "Packaged tools for extracting, loading, and transforming data across systems. This dimension covers connector-based ingestion, transformation frameworks, and managed integration products.",
            "slug": "etl-and-elt-tooling",
            "source": "db"
          },
          "input_skill": "Informatica",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Data Engineer",
              "id": 2,
              "rationale": null,
              "role_archetype": null,
              "slug": "data-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "Informatica",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [
        {
          "alias_text": "DevOps",
          "alias_type": "CANONICAL",
          "id": 1852,
          "is_primary": false,
          "match_strategy": "CASE_INSENSITIVE"
        }
      ],
      "canonical": {
        "category_id": 8,
        "display_name": "DevOps",
        "id": 1216,
        "is_also_category": false,
        "is_extractable": true,
        "skill_nature": "METHODOLOGY",
        "slug": "devops",
        "sub_category_id": 922,
        "typical_lifespan": "EVERGREEN",
        "volatility": "STABLE"
      },
      "dimensions": [
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "CI/CD Pipeline Platforms",
            "id": 150,
            "rationale": "Systems used to define, run, and maintain automated build and deployment workflows. This cluster is coherent because the role owns delivery automation end to end, including pipeline reliability and promotion logic.",
            "slug": "ci-cd-pipeline-platforms",
            "source": "db"
          },
          "input_skill": "DevOps",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "DevOps Engineer",
              "id": 10,
              "rationale": null,
              "role_archetype": null,
              "slug": "devops-engineer",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Deployment and Release Patterns",
            "id": 140,
            "rationale": "Patterns for promoting changes safely across environments, including rollout, rollback, and release gating strategies. Cloud Architects define these patterns so teams can deploy consistently across the platform.",
            "slug": "deployment-and-release-patterns",
            "source": "db"
          },
          "input_skill": "DevOps",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Cloud Architect",
              "id": 9,
              "rationale": null,
              "role_archetype": null,
              "slug": "cloud-architect",
              "source": "db"
            }
          ]
        },
        {
          "dimension": {
            "difficulty_hint": "well_known",
            "display_name": "Infrastructure as Code",
            "id": 132,
            "rationale": "Declarative provisioning and environment definition tools used to codify cloud infrastructure, repeatable environments, and platform standards. Cloud Architects use these to express reference architectures and guardrails.",
            "slug": "infrastructure-as-code",
            "source": "db"
          },
          "input_skill": "DevOps",
          "llm_role": null,
          "roles_from_db": [
            {
              "display_name": "Cloud Architect",
              "id": 9,
              "rationale": null,
              "role_archetype": null,
              "slug": "cloud-architect",
              "source": "db"
            },
            {
              "display_name": "DevOps Engineer",
              "id": 10,
              "rationale": null,
              "role_archetype": null,
              "slug": "devops-engineer",
              "source": "db"
            }
          ]
        }
      ],
      "input_skill": "DevOps",
      "matched_via": "alias",
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": null,
      "source_tag": "db",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [],
      "canonical": null,
      "dimensions": [],
      "input_skill": "Master Data Management",
      "matched_via": null,
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": {
        "derived": {
          "category": "Data Governance",
          "skill_nature": "CONCEPT",
          "sub_category": "general",
          "typical_lifespan": "MULTI_YEAR",
          "version_strategy": "UNVERSIONED",
          "volatility": "MEDIUM"
        },
        "enrichment": null,
        "keep_log": [],
        "locked_dimensions": [],
        "merge_log": [],
        "placed": null,
        "relationships": null,
        "skill_id": "master-data-management",
        "split_log": [],
        "typed": null,
        "warnings": []
      },
      "source_tag": "llm",
      "was_in_llm_skills": true
    },
    {
      "aliases_in_db": [],
      "canonical": null,
      "dimensions": [],
      "input_skill": "Data Governance",
      "matched_via": null,
      "new_alias_persisted": false,
      "new_alias_text": null,
      "new_skill_meta": {
        "derived": {
          "category": "Data Governance",
          "skill_nature": "CONCEPT",
          "sub_category": "general",
          "typical_lifespan": "MULTI_YEAR",
          "version_strategy": "UNVERSIONED",
          "volatility": "MEDIUM"
        },
        "enrichment": null,
        "keep_log": [],
        "locked_dimensions": [],
        "merge_log": [],
        "placed": null,
        "relationships": null,
        "skill_id": "data-governance",
        "split_log": [],
        "typed": null,
        "warnings": []
      },
      "source_tag": "llm",
      "was_in_llm_skills": true
    }
  ],
  "unmatched_skills": [
    "Master Data Management",
    "Data Governance"
  ]
}
API 3 — final-role-output
{
  "chosen_role": {
    "display_name": "Data Governance Engineer",
    "id": 146,
    "rationale": "Domain=Data Engineering \u0026 Analytics; The JD centers on master data management, data governance, information architecture, match-and-merge rules, and MDM solution oversight, which best aligns with Data Governance Engineer.",
    "role_archetype": null,
    "slug": "data-governance-engineer",
    "source": "db"
  },
  "chosen_role_resolution": "in_db",
  "final_input_skills": [
    {
      "skill": "Informatica",
      "tag": "in_db"
    },
    {
      "skill": "DevOps",
      "tag": "in_db"
    },
    {
      "skill": "Master Data Management",
      "tag": "new"
    },
    {
      "skill": "Data Governance",
      "tag": "new"
    }
  ],
  "llm_cost_api1_usd": null,
  "llm_cost_api2_usd": null,
  "llm_cost_api3_usd": null,
  "llm_cost_total_usd": null,
  "persistence": {
    "items": [
      {
        "chosen_role_id": 146,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "ETL and ELT Tooling",
          "id": 24,
          "rationale": "Packaged tools for extracting, loading, and transforming data across systems. This dimension covers connector-based ingestion, transformation frameworks, and managed integration products.",
          "slug": "etl-and-elt-tooling",
          "source": "db"
        },
        "dimension_id": 24,
        "input_skill": "Informatica",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Data Engineer",
            "id": 2,
            "rationale": null,
            "role_archetype": null,
            "slug": "data-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 117,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 146,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "CI/CD Pipeline Platforms",
          "id": 150,
          "rationale": "Systems used to define, run, and maintain automated build and deployment workflows. This cluster is coherent because the role owns delivery automation end to end, including pipeline reliability and promotion logic.",
          "slug": "ci-cd-pipeline-platforms",
          "source": "db"
        },
        "dimension_id": 150,
        "input_skill": "DevOps",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "DevOps Engineer",
            "id": 10,
            "rationale": null,
            "role_archetype": null,
            "slug": "devops-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 1216,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 146,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Deployment and Release Patterns",
          "id": 140,
          "rationale": "Patterns for promoting changes safely across environments, including rollout, rollback, and release gating strategies. Cloud Architects define these patterns so teams can deploy consistently across the platform.",
          "slug": "deployment-and-release-patterns",
          "source": "db"
        },
        "dimension_id": 140,
        "input_skill": "DevOps",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Cloud Architect",
            "id": 9,
            "rationale": null,
            "role_archetype": null,
            "slug": "cloud-architect",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 1216,
        "skill_tag": "in_db",
        "skipped_reason": null
      },
      {
        "chosen_role_id": 146,
        "dimension": {
          "difficulty_hint": "well_known",
          "display_name": "Infrastructure as Code",
          "id": 132,
          "rationale": "Declarative provisioning and environment definition tools used to codify cloud infrastructure, repeatable environments, and platform standards. Cloud Architects use these to express reference architectures and guardrails.",
          "slug": "infrastructure-as-code",
          "source": "db"
        },
        "dimension_id": 132,
        "input_skill": "DevOps",
        "llm_role": null,
        "matched_chosen_role": false,
        "outcome_line": "Existing dimension (library) \u00b7 Role\u2194dimension skipped (dimension not under chosen role)",
        "role_dimension_saved": false,
        "roles_from_db": [
          {
            "display_name": "Cloud Architect",
            "id": 9,
            "rationale": null,
            "role_archetype": null,
            "slug": "cloud-architect",
            "source": "db"
          },
          {
            "display_name": "DevOps Engineer",
            "id": 10,
            "rationale": null,
            "role_archetype": null,
            "slug": "devops-engineer",
            "source": "db"
          }
        ],
        "skill_dimension_saved": true,
        "skill_id": 1216,
        "skill_tag": "in_db",
        "skipped_reason": null
      }
    ],
    "new_skills_created": 0,
    "role_dimension_saved": 0,
    "skill_dimension_saved": 0,
    "skipped": 0
  },
  "planner_output": null,
  "run_id": "fc3d1b12-2b6c-4d63-bcec-f2574b117d97"
}