← Back to history

Pipeline run

b59f4bd2-2627-4326-a65a-eda8d863332b

Pipeline LLM cost (USD)
API 1: $0.0043 API 2: $0.0000 API 3: $0.0000 Total: $0.0043

Client output enrichment

v2 Skill cluster · Nature of work · AI index · Tech stack maturity · Evidence · KRA description
role baseline loaded sources · ai_index: jd · nature_of_work: jd · tech_stack_maturity: jd
Nature of work · Data pipeline development
Migrates and tests Big Data/ETL pipelines into Snowflake lakehouse, writing SQL/Snowpark/DBT transforms, fixing defects, tuning performance, and automating CI/CD and scheduled workflows.
""migrating & testing applications on Snowflake, Snowpark, Apache Spark, Hive , on new retail banking data Lakehouse""
Tech stack maturity
Mainstream Modern cache hit
Snowflake and SQL are widely adopted, current data-platform technologies that fit a mainstream modern stack rather than legacy or bleeding-edge.
AI index (0 = no AI use, 5 = totally AI-dependent · v2.1)
0.00 / 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):
Evidence — skills matched in JD (19)
Snowflake Snowpark SQL ETL ELT dbt Apache Spark Hive HDFS Jenkins Control-M CI/CD Agile Azure Scala Python Hadoop Data Modeling Distributed Computing
Skill cluster (5 dimension groups, role-scoped)
ETL and ELT Tooling
dbt Apache Spark Hadoop
Programming Languages for Data Work
SQL Scala Python
Cloud Data Warehouses
Snowflake
Cloud Platforms
Azure
Cross-cutting / unaligned
Snowpark ETL ELT Hive HDFS Jenkins Control-M CI/CD Agile Data Modeling Distributed Computing
Show KRA description ↓
We are seeking an experienced Data Engineer with strong Snowflake skills to join our data engineering team. The ideal candidate will have a solid background in data ingestion, data processing, and data management using technologies such as Snowflake, Snowpark,DBT . Knowledge on Apache Spark, Hive, and HDFS would be good to have.. You will be responsible for migrating and testing data pipelines and ensuring efficient data storage and processing. In addition, you will work with CI/CD tools, such as Jenkins, and schedulers like CTRL-M, to automate data workflows. Responsibilities • Will work as an Individual contributor on Big Data Migration Project to Lakehouse migration project. • Perform tasks related to migrating & testing applications on Snowflake, Snowpark, Apache Spark, Hive , on new retail banking data Lakehouse. • Good to have knowledge on DBT. • Perform extensive testing of the migrated code, debugging & fixing issues. • Manage DevOPS as required & defined on the project • Automate processes wherever required to improve efficiency of testing team. • Co-ordinate with diverse geographically located teams to complete assigned activities. • Participate in daily various agile ceremonies during the ongoing sprint and complete tasks as required. • Conduct bug-free release validations and produce metrics, tests, and defect reports. • Assist in developing and enforcing team guidelines. • Being spoc for the team and provide information/status on ongoing activities on regular basis to management whenever needed. • At least 3 to 7 Years of experience on big data platform and at least 2 years of experience in implementing DWH on Snowflake • Proven experience with cloud platforms preferable Azure particularly on data services • Good understanding of distributed computing frameworks like Apache Spark, Hadoop etc • Perform Analysis on existing data storage systems Big Data & development of data solutions in Snowflake • High Proficiency in SQL and at least one of the following languages Scala / Python & • Experience in working on migrating data from on-premise databases preferably Big Data platformto Snowflake • Expertise in building robust ELT/ETL processes , performance tuning of the data pipelines in Snowflake and should be able to trouble shoot the issues quickly • Strong Knowledge on Integration concepts and design best practices • Data Modeling & data integration, Advanced SQL skills for analysis, standardizing queries • Proven experience in managing and mentoring data engineering teams • Excellent interpersonal skills, with the ability to work across teams and communicate effectively with technical and non-technical stake holders • Strong analytical and trouble shooting skills with proven ability to find solutions in complex data environments

Signals

Skill data-engineer
0.40
Alias data-engineer
1.00
KRA data-engineer
0.61

Post-classification

Centroidupdated · n=247
Alias collision log
New-role queue
New skills captured7
New KRA captured

Captured for admin review

Snowpark primary Data Engineer pending
HDFS Data Engineer pending
Control-M Data Engineer pending
ETL primary Data Engineer pending
ELT primary Data Engineer pending
Data Modeling Data Engineer pending
Distributed Computing Data Engineer pending
Status: extract_from_jd_done Created: 2026-05-27T15:03:28.309876Z Updated: 2026-06-12T16:56:22.442151Z
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

No chosen role stored for this run.

Job description

Reference 25000HVJ

 Responsibilities

We are seeking an experienced Data Engineer with strong Snowflake skills to join our data engineering team. The ideal candidate will have a solid background in data ingestion, data processing, and data management using technologies such as Snowflake, Snowpark,DBT .

Knowledge on Apache Spark, Hive, and HDFS would be good to have.. You will be responsible for migrating and testing data pipelines and ensuring efficient data storage and processing. In addition, you will work with CI/CD tools, such as Jenkins, and schedulers like CTRL-M, to automate data workflows.

Responsibilities

• Will work as an Individual contributor on Big Data Migration Project to Lakehouse migration project.
• Perform tasks related to migrating & testing applications on Snowflake, Snowpark, Apache Spark, Hive , on new retail banking data Lakehouse.
• Good to have knowledge on DBT.
• Perform extensive testing of the migrated code, debugging & fixing issues.
• Manage DevOPS as required & defined on the project
• Automate processes wherever required to improve efficiency of testing team.
• Co-ordinate with diverse geographically located teams to complete assigned activities.
• Participate in daily various agile ceremonies during the ongoing sprint and complete tasks as required.
• Conduct bug-free release validations and produce metrics, tests, and defect reports.
• Assist in developing and enforcing team guidelines.
• Being spoc for the team and provide information/status on ongoing activities on regular basis to management whenever needed.


 Profile Required

• At least 3 to 7 Years of experience on big data platform and at least 2 years of experience in implementing DWH on Snowflake
• Proven experience with cloud platforms preferable Azure particularly on data services
• Good understanding of distributed computing frameworks like Apache Spark, Hadoop etc
• Perform Analysis on existing data storage systems Big Data & development of data solutions in Snowflake
• High Proficiency in SQL and at least one of the following languages Scala / Python &
• Experience in working on migrating data from on-premise databases preferably Big Data platformto Snowflake
• Expertise in building robust ELT/ETL processes , performance tuning of the data pipelines in Snowflake and should be able to trouble shoot the issues quickly
• Strong Knowledge on Integration concepts and design best practices
• Data Modeling & data integration, Advanced SQL skills for analysis, standardizing queries
• Proven experience in managing and mentoring data engineering teams
• Excellent interpersonal skills, with the ability to work across teams and communicate effectively with technical and non-technical stake holders
• Strong analytical and trouble shooting skills with proven ability to find solutions in complex data environments


 Why join us

We are committed to creating a diverse environment and are proud to be an equal opportunity employer. All qualified applicants receive consideration for employment without regard to race, color, religion, gender, gender identity or expression, sexual orientation, national origin, genetics, disability, age, or veteran status

 Business insight

At Société Générale, we are convinced that people are drivers of change, and that the world of tomorrow will be shaped by all their initiatives, from the smallest to the most ambitious. Whether you’re joining us for a period of months, years or your entire career, together we can have a positive impact on the future. Creating, daring, innovating, and taking action are part of our DNA. If you too want to be directly involved, grow in a stimulating and caring environment, feel useful on a daily basis and develop or strengthen your expertise, you will feel right at home with us!

Still hesitating?

You should know that our employees can dedicate several days per year to solidarity actions during their working hours, including sponsoring people struggling with their orientation or professional integration, participating in the financial education of young apprentices, and sharing their skills with charities. There are many ways to get involved.

We are committed to support accelerating our Group’s ESG strategy by implementing ESG principles in all our activities and policies. They are translated in our business activity (ESG assessment, reporting, project management or IT activities), our work environment and in our responsible practices for environment protection.

 Diversity and Inclusion

We are an equal opportunities employer and we are proud to make diversity a strength for our company. Societe Generale is committed to recognizing and promoting all talents, regardless of their beliefs, age, disability, parental status, ethnic origin, nationality, gender identity, sexual orientation, membership of a political, religious, trade union or minority organisation, or any other characteristic that could be subject to discrimination.

Skills from this JD

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

Snowflake Primary No API 2 row (run stopped after API 1 or history missing)
Snowpark Primary No API 2 row (run stopped after API 1 or history missing)
dbt Secondary No API 2 row (run stopped after API 1 or history missing)
Apache Spark Secondary No API 2 row (run stopped after API 1 or history missing)
Hive Secondary No API 2 row (run stopped after API 1 or history missing)
HDFS Secondary No API 2 row (run stopped after API 1 or history missing)
Jenkins Secondary No API 2 row (run stopped after API 1 or history missing)
Control-M Secondary No API 2 row (run stopped after API 1 or history missing)
CI/CD Secondary No API 2 row (run stopped after API 1 or history missing)
Agile Secondary No API 2 row (run stopped after API 1 or history missing)
Azure Secondary No API 2 row (run stopped after API 1 or history missing)
SQL Primary No API 2 row (run stopped after API 1 or history missing)
Scala Secondary No API 2 row (run stopped after API 1 or history missing)
Python Secondary No API 2 row (run stopped after API 1 or history missing)
Hadoop Secondary No API 2 row (run stopped after API 1 or history missing)
ETL Primary No API 2 row (run stopped after API 1 or history missing)
ELT Primary No API 2 row (run stopped after API 1 or history missing)
Data Modeling Secondary No API 2 row (run stopped after API 1 or history missing)
Distributed Computing Secondary No API 2 row (run stopped after API 1 or history missing)

Library artifacts (this run)

No artifact rows for this run.
nano JD Parser — gpt-4.1-nano click to toggle
RoleData Engineer
CompanySociété Générale
ExperienceAt least 3 to 7 Years of experience on big data platform
DomainFinancial Services
JD type pass
Show raw JSON
{
  "JD_type": "pass",
  "about_company": {
    "source_marker": {
      "first_5_words": "At Soci\u00e9t\u00e9 G\u00e9n\u00e9rale, we are",
      "last_5_words": "feel right at home with us!"
    },
    "text": "At Soci\u00e9t\u00e9 G\u00e9n\u00e9rale, we are convinced that people are drivers of change, and that the world of tomorrow will be shaped by all their initiatives, from the smallest to the most ambitious. Whether you\u2019re joining us for a period of months, years or your entire career, together we can have a positive impact on the future. Creating, daring, innovating, and taking action are part of our DNA. If you too want to be directly involved, grow in a stimulating and caring environment, feel useful on a daily basis and develop or strengthen your expertise, you will feel right at home with us!",
    "word_count": 84
  },
  "certifications": [],
  "company_name": "Soci\u00e9t\u00e9 G\u00e9n\u00e9rale",
  "ctc": null,
  "domain": {
    "primary": {
      "aliases": [
        "FinTech",
        "Banking"
      ],
      "domain": "Financial Services"
    },
    "secondary": null
  },
  "education": [],
  "experience": {
    "max": 7,
    "min": 3,
    "raw": "At least 3 to 7 Years of experience on big data platform"
  },
  "job_locations": [],
  "role": "Data Engineer",
  "role_aliases": [
    "Big Data Engineer",
    "Data Engineer",
    "Data Developer"
  ],
  "role_archetype": "Data",
  "roles_and_responsibilities": [
    {
      "bullet_count": 11,
      "heading": "Responsibilities",
      "heading_was_present": true,
      "source_marker": {
        "first_5_words": "We are seeking an experienced",
        "last_5_words": "activities on regular basis to"
      },
      "text": "We are seeking an experienced Data Engineer with strong Snowflake skills to join our data engineering team. The ideal candidate will have a solid background in data ingestion, data processing, and data management using technologies such as Snowflake, Snowpark,DBT .\n\nKnowledge on Apache Spark, Hive, and HDFS would be good to have.. You will be responsible for migrating and testing data pipelines and ensuring efficient data storage and processing. In addition, you will work with CI/CD tools, such as Jenkins, and schedulers like CTRL-M, to automate data workflows.\n\nResponsibilities\n\n\u2022 Will work as an Individual contributor on Big Data Migration Project to Lakehouse migration project.\n\u2022 Perform tasks related to migrating \u0026 testing applications on Snowflake, Snowpark, Apache Spark, Hive , on new retail banking data Lakehouse.\n\u2022 Good to have knowledge on DBT.\n\u2022 Perform extensive testing of the migrated code, debugging \u0026 fixing issues.\n\u2022 Manage DevOPS as required \u0026 defined on the project\n\u2022 Automate processes wherever required to improve efficiency of testing team.\n\u2022 Co-ordinate with diverse geographically located teams to complete assigned activities.\n\u2022 Participate in daily various agile ceremonies during the ongoing sprint and complete tasks as required.\n\u2022 Conduct bug-free release validations and produce metrics, tests, and defect reports.\n\u2022 Assist in developing and enforcing team guidelines.\n\u2022 Being spoc for the team and provide information/status on ongoing activities on regular basis to management whenever needed.",
      "word_count": 335
    },
    {
      "bullet_count": 11,
      "heading": "Profile Required",
      "heading_was_present": true,
      "source_marker": {
        "first_5_words": "\u2022 At least 3 to 7",
        "last_5_words": "in complex data environments"
      },
      "text": "\u2022 At least 3 to 7 Years of experience on big data platform and at least 2 years of experience in implementing DWH on Snowflake\n\u2022 Proven experience with cloud platforms preferable Azure particularly on data services\n\u2022 Good understanding of distributed computing frameworks like Apache Spark, Hadoop etc\n\u2022 Perform Analysis on existing data storage systems Big Data \u0026 development of data solutions in Snowflake\n\u2022 High Proficiency in SQL and at least one of the following languages Scala / Python \u0026\n\u2022 Experience in working on migrating data from on-premise databases preferably Big Data platformto Snowflake\n\u2022 Expertise in building robust ELT/ETL processes , performance tuning of the data pipelines in Snowflake and should be able to trouble shoot the issues quickly\n\u2022 Strong Knowledge on Integration concepts and design best practices\n\u2022 Data Modeling \u0026 data integration, Advanced SQL skills for analysis, standardizing queries\n\u2022 Proven experience in managing and mentoring data engineering teams\n\u2022 Excellent interpersonal skills, with the ability to work across teams and communicate effectively with technical and non-technical stake holders\n\u2022 Strong analytical and trouble shooting skills with proven ability to find solutions in complex data environments",
      "word_count": 236
    }
  ],
  "urls": []
}
API 1 — extract-from-jd click to toggle
{
  "final_skills": [
    {
      "is_primary": true,
      "skill_name": "Snowflake"
    },
    {
      "is_primary": true,
      "skill_name": "Snowpark"
    },
    {
      "is_primary": false,
      "skill_name": "dbt"
    },
    {
      "is_primary": false,
      "skill_name": "Apache Spark"
    },
    {
      "is_primary": false,
      "skill_name": "Hive"
    },
    {
      "is_primary": false,
      "skill_name": "HDFS"
    },
    {
      "is_primary": false,
      "skill_name": "Jenkins"
    },
    {
      "is_primary": false,
      "skill_name": "Control-M"
    },
    {
      "is_primary": false,
      "skill_name": "CI/CD"
    },
    {
      "is_primary": false,
      "skill_name": "Agile"
    },
    {
      "is_primary": false,
      "skill_name": "Azure"
    },
    {
      "is_primary": true,
      "skill_name": "SQL"
    },
    {
      "is_primary": false,
      "skill_name": "Scala"
    },
    {
      "is_primary": false,
      "skill_name": "Python"
    },
    {
      "is_primary": false,
      "skill_name": "Hadoop"
    },
    {
      "is_primary": true,
      "skill_name": "ETL"
    },
    {
      "is_primary": true,
      "skill_name": "ELT"
    },
    {
      "is_primary": false,
      "skill_name": "Data Modeling"
    },
    {
      "is_primary": false,
      "skill_name": "Distributed Computing"
    }
  ],
  "jd_role": {
    "display_name": "Data Engineer",
    "rationale": null,
    "role_aliases": [
      "Big Data Engineer",
      "Data Engineer",
      "Data Developer"
    ],
    "role_archetype": "Data",
    "slug": ""
  },
  "nano_parsed": {
    "JD_type": "pass",
    "about_company": {
      "source_marker": {
        "first_5_words": "At Soci\u00e9t\u00e9 G\u00e9n\u00e9rale, we are",
        "last_5_words": "feel right at home with us!"
      },
      "text": "At Soci\u00e9t\u00e9 G\u00e9n\u00e9rale, we are convinced that people are drivers of change, and that the world of tomorrow will be shaped by all their initiatives, from the smallest to the most ambitious. Whether you\u2019re joining us for a period of months, years or your entire career, together we can have a positive impact on the future. Creating, daring, innovating, and taking action are part of our DNA. If you too want to be directly involved, grow in a stimulating and caring environment, feel useful on a daily basis and develop or strengthen your expertise, you will feel right at home with us!",
      "word_count": 84
    },
    "certifications": [],
    "company_name": "Soci\u00e9t\u00e9 G\u00e9n\u00e9rale",
    "ctc": null,
    "domain": {
      "primary": {
        "aliases": [
          "FinTech",
          "Banking"
        ],
        "domain": "Financial Services"
      },
      "secondary": null
    },
    "education": [],
    "experience": {
      "max": 7,
      "min": 3,
      "raw": "At least 3 to 7 Years of experience on big data platform"
    },
    "job_locations": [],
    "role": "Data Engineer",
    "role_aliases": [
      "Big Data Engineer",
      "Data Engineer",
      "Data Developer"
    ],
    "role_archetype": "Data",
    "roles_and_responsibilities": [
      {
        "bullet_count": 11,
        "heading": "Responsibilities",
        "heading_was_present": true,
        "source_marker": {
          "first_5_words": "We are seeking an experienced",
          "last_5_words": "activities on regular basis to"
        },
        "text": "We are seeking an experienced Data Engineer with strong Snowflake skills to join our data engineering team. The ideal candidate will have a solid background in data ingestion, data processing, and data management using technologies such as Snowflake, Snowpark,DBT .\n\nKnowledge on Apache Spark, Hive, and HDFS would be good to have.. You will be responsible for migrating and testing data pipelines and ensuring efficient data storage and processing. In addition, you will work with CI/CD tools, such as Jenkins, and schedulers like CTRL-M, to automate data workflows.\n\nResponsibilities\n\n\u2022 Will work as an Individual contributor on Big Data Migration Project to Lakehouse migration project.\n\u2022 Perform tasks related to migrating \u0026 testing applications on Snowflake, Snowpark, Apache Spark, Hive , on new retail banking data Lakehouse.\n\u2022 Good to have knowledge on DBT.\n\u2022 Perform extensive testing of the migrated code, debugging \u0026 fixing issues.\n\u2022 Manage DevOPS as required \u0026 defined on the project\n\u2022 Automate processes wherever required to improve efficiency of testing team.\n\u2022 Co-ordinate with diverse geographically located teams to complete assigned activities.\n\u2022 Participate in daily various agile ceremonies during the ongoing sprint and complete tasks as required.\n\u2022 Conduct bug-free release validations and produce metrics, tests, and defect reports.\n\u2022 Assist in developing and enforcing team guidelines.\n\u2022 Being spoc for the team and provide information/status on ongoing activities on regular basis to management whenever needed.",
        "word_count": 335
      },
      {
        "bullet_count": 11,
        "heading": "Profile Required",
        "heading_was_present": true,
        "source_marker": {
          "first_5_words": "\u2022 At least 3 to 7",
          "last_5_words": "in complex data environments"
        },
        "text": "\u2022 At least 3 to 7 Years of experience on big data platform and at least 2 years of experience in implementing DWH on Snowflake\n\u2022 Proven experience with cloud platforms preferable Azure particularly on data services\n\u2022 Good understanding of distributed computing frameworks like Apache Spark, Hadoop etc\n\u2022 Perform Analysis on existing data storage systems Big Data \u0026 development of data solutions in Snowflake\n\u2022 High Proficiency in SQL and at least one of the following languages Scala / Python \u0026\n\u2022 Experience in working on migrating data from on-premise databases preferably Big Data platformto Snowflake\n\u2022 Expertise in building robust ELT/ETL processes , performance tuning of the data pipelines in Snowflake and should be able to trouble shoot the issues quickly\n\u2022 Strong Knowledge on Integration concepts and design best practices\n\u2022 Data Modeling \u0026 data integration, Advanced SQL skills for analysis, standardizing queries\n\u2022 Proven experience in managing and mentoring data engineering teams\n\u2022 Excellent interpersonal skills, with the ability to work across teams and communicate effectively with technical and non-technical stake holders\n\u2022 Strong analytical and trouble shooting skills with proven ability to find solutions in complex data environments",
        "word_count": 236
      }
    ],
    "urls": []
  },
  "rejected": false,
  "rejection_reason": null,
  "run_id": "b59f4bd2-2627-4326-a65a-eda8d863332b",
  "stage3_signals": {
    "alias_found": true,
    "alias_match_roles": [
      {
        "display_name": "Data Engineer",
        "kra_matches": null,
        "matched_count": null,
        "matched_skills": null,
        "role_id": 2,
        "score": 1.0,
        "slug": "data-engineer",
        "total_count": null
      }
    ],
    "kra_match_roles": [
      {
        "display_name": "Data Engineer",
        "kra_matches": [
          {
            "kra_text": "Develops batch and real-time streaming data pipelines using Apache Spark, Apache Kafka, Apache Flink, or Airflow for data movement and processing at scale.",
            "sentence": "Perform tasks related to migrating \u0026 testing applications on Snowflake, Snowpark, Apache Spark, Hive , on new retail banking data Lakehouse.",
            "similarity": 0.6182
          },
          {
            "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": "Data Modeling \u0026 data integration, Advanced SQL skills for analysis, standardizing queries",
            "similarity": 0.6092
          },
          {
            "kra_text": "Optimizes pipeline throughput, partitioning strategies, and query performance across cloud data warehouses like Snowflake, BigQuery, or Redshift.",
            "sentence": "Perform Analysis on existing data storage systems Big Data \u0026 development of data solutions in Snowflake",
            "similarity": 0.6062
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 2,
        "score": 0.6112,
        "slug": "data-engineer",
        "total_count": null
      },
      {
        "display_name": "DevOps Engineer",
        "kra_matches": [
          {
            "kra_text": "Builds and maintains CI/CD pipelines using Jenkins, GitHub Actions, GitLab CI, or CircleCI to automate build, test, security scanning, and deployment workflows.",
            "sentence": "In addition, you will work with CI/CD tools, such as Jenkins, and schedulers like CTRL-M, to automate data workflows.",
            "similarity": 0.5751
          },
          {
            "kra_text": "Collaborates with development teams to improve build processes, reduce deployment friction, containerize applications, and adopt DevOps best practices.",
            "sentence": "Manage DevOPS as required \u0026 defined on the project",
            "similarity": 0.5503
          },
          {
            "kra_text": "Monitors CI/CD pipeline reliability, identifies bottlenecks in delivery workflows, and improves deployment frequency, lead time, and failure recovery rate.",
            "sentence": "Conduct bug-free release validations and produce metrics, tests, and defect reports.",
            "similarity": 0.5295
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 10,
        "score": 0.5516,
        "slug": "devops-engineer",
        "total_count": null
      },
      {
        "display_name": "MLOps Engineer",
        "kra_matches": [
          {
            "kra_text": "Validates model performance benchmarks, data schema contracts, and system integration health before signing off on production release readiness.",
            "sentence": "Conduct bug-free release validations and produce metrics, tests, and defect reports.",
            "similarity": 0.5998
          },
          {
            "kra_text": "Coordinates model promotion workflows across development, staging, and production environments including integration testing and data contract validation.",
            "sentence": "Manage DevOPS as required \u0026 defined on the project",
            "similarity": 0.5129
          },
          {
            "kra_text": "Automates ML platform operations including scheduled retraining triggers, pipeline orchestration, evaluation workflows, and alerting configuration.",
            "sentence": "In addition, you will work with CI/CD tools, such as Jenkins, and schedulers like CTRL-M, to automate data workflows.",
            "similarity": 0.5114
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 16,
        "score": 0.5413,
        "slug": "ml-ops-engineer",
        "total_count": null
      },
      {
        "display_name": "Java Backend Developer",
        "kra_matches": [
          {
            "kra_text": "code refactoring and defect fixes",
            "sentence": "Perform extensive testing of the migrated code, debugging \u0026 fixing issues.",
            "similarity": 0.5484
          },
          {
            "kra_text": "persistence and data modeling",
            "sentence": "Data Modeling \u0026 data integration, Advanced SQL skills for analysis, standardizing queries",
            "similarity": 0.5264
          },
          {
            "kra_text": "code refactoring and defect fixes",
            "sentence": "Conduct bug-free release validations and produce metrics, tests, and defect reports.",
            "similarity": 0.5193
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 79,
        "score": 0.5313,
        "slug": "java-backend-developer",
        "total_count": null
      },
      {
        "display_name": "Drupal Dev",
        "kra_matches": [
          {
            "kra_text": "site troubleshooting and defect fixes",
            "sentence": "Perform extensive testing of the migrated code, debugging \u0026 fixing issues.",
            "similarity": 0.5598
          },
          {
            "kra_text": "site troubleshooting and defect fixes",
            "sentence": "Conduct bug-free release validations and produce metrics, tests, and defect reports.",
            "similarity": 0.5096
          },
          {
            "kra_text": "external system integration",
            "sentence": "Strong Knowledge on Integration concepts and design best practices",
            "similarity": 0.4797
          }
        ],
        "matched_count": null,
        "matched_skills": null,
        "role_id": 228,
        "score": 0.5164,
        "slug": "drupal-dev",
        "total_count": null
      }
    ],
    "skill_match_roles": [
      {
        "display_name": "Data Engineer",
        "kra_matches": null,
        "matched_count": 2,
        "matched_skills": [
          "SQL",
          "Snowflake"
        ],
        "role_id": 2,
        "score": 0.4,
        "slug": "data-engineer",
        "total_count": 5
      },
      {
        "display_name": "Pega Developer",
        "kra_matches": null,
        "matched_count": 1,
        "matched_skills": [
          "SQL"
        ],
        "role_id": 24,
        "score": 0.2,
        "slug": "pega-developer",
        "total_count": 5
      },
      {
        "display_name": "Engineering Manager",
        "kra_matches": null,
        "matched_count": 1,
        "matched_skills": [
          "SQL"
        ],
        "role_id": 121,
        "score": 0.2,
        "slug": "engineering-manager",
        "total_count": 5
      }
    ]
  },
  "stage4_decision": {
    "alias_collision_detected": false,
    "case": "A",
    "chosen_role": {
      "display_name": "Data Engineer",
      "kra_matches": null,
      "matched_count": null,
      "matched_skills": null,
      "role_id": 2,
      "score": 1.0,
      "slug": "data-engineer",
      "total_count": null
    },
    "confidence": 1.0,
    "is_new_role": false,
    "llm2_fired": false,
    "llm2_reasoning": null,
    "matched_dimensions": [],
    "matched_kras": [],
    "matched_skills": [],
    "new_role_display_name": null,
    "new_role_slug": null,
    "queued": false,
    "reasoning": "Exact alias hit on data-engineer (1.0) \u2014 no other alias at this confidence; skill_top data-engineer 0.40 does not contradict",
    "sub_role": null
  },
  "stage5_updates": {
    "centroid_n_after": 247,
    "centroid_updated": true,
    "collision_log_id": null,
    "new_kra_attached": null,
    "new_skills_attached": [
      {
        "is_primary": true,
        "queue_id": 12334,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "Snowpark",
        "status": "pending"
      },
      {
        "is_primary": false,
        "queue_id": 12335,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "HDFS",
        "status": "pending"
      },
      {
        "is_primary": false,
        "queue_id": 12336,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "Control-M",
        "status": "pending"
      },
      {
        "is_primary": true,
        "queue_id": 12337,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "ETL",
        "status": "pending"
      },
      {
        "is_primary": true,
        "queue_id": 12338,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "ELT",
        "status": "pending"
      },
      {
        "is_primary": false,
        "queue_id": 12339,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "Data Modeling",
        "status": "pending"
      },
      {
        "is_primary": false,
        "queue_id": 12340,
        "role_display_name": "Data Engineer",
        "role_slug": "data-engineer",
        "skill_name": "Distributed Computing",
        "status": "pending"
      }
    ],
    "queue_entry_id": null,
    "v3_pipeline_triggered": false,
    "v3_role_slug": null,
    "v3_run_id": null
  }
}
API 2 — extract-details
{}
API 3 — final-role-output
{}

LLM Calls

Every model call made for this run, in pipeline order. Click a card to see the model's response.

Loading…