Pipeline run

830267ff-1c70-492f-84f3-48519722a847

Pipeline LLM cost (USD)

API 1: $0.0035 API 2: $0.0000 API 3: $0.0000 Total: $0.0035

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 · AI Application & RAG Engineering

Build LLM-based apps and chat agents over structured data, create RAG pipelines with vector stores, and wire in LangChain/LlamaIndex/CrewAI plus OpenAI/Azure/Anthropic/Hugging Face APIs; also set up model versioning and MLflow.

""Develop RAG pipelines using vector stores (Pinecone, FAISS, ChromaDB)""

Tech stack maturity

AI-Native & Bleeding-Edge

The skill set is centered on contemporary AI/LLM tooling and cloud AI platforms such as Anthropic, OpenAI, Azure OpenAI, LangChain, LlamaIndex, CrewAI, vector databases, and MLOps, which strongly indicates an AI-native modern stack.

AI index (0 = no AI use, 5 = totally AI-dependent · v2.1)

3.20 / 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): LangChain, LlamaIndex, Hugging Face, Azure OpenAI, CrewAI, Pinecone

Models / concepts (×3): Anthropic, OpenAI, RAG, LLMs, MLOps, AI

Evidence — skills matched in JD (21)

Python SQL Snowflake Pinecone FAISS ChromaDB LangChain LlamaIndex OpenAI Azure OpenAI Anthropic Hugging Face PostgreSQL MySQL Git Docker MLflow AWS Azure GCP CrewAI

Skill cluster (9 dimension groups, role-scoped)

Cloud Platforms for AI Deployment

AWS Azure GCP

LLM Operations and Orchestration

Pinecone LangChain LlamaIndex

ML Frameworks and Libraries

FAISS Hugging Face

Relational Database Usage

PostgreSQL MySQL

Agentic Frameworks

CrewAI

Containerization and Image Builds

Docker

LLM Provider APIs

Azure OpenAI

Python Programming

Python

Cross-cutting / unaligned

SQL Snowflake ChromaDB OpenAI Anthropic Git MLflow

Show KRA description ↓

- Design and build AI-powered applications and conversational agents using LLMs to interact with structured data sources - Develop RAG pipelines using vector stores (Pinecone, FAISS, ChromaDB) - Integrate frameworks like LangChain, LlamaIndex, CrewAI - Work with OpenAI, Azure OpenAI, Anthropic, Hugging Face APIs - Set up MLOps practices (model versioning, MLflow) Python, SQL, Snowflake, Pinecone, FAISS, ChromaDB, LangChain, LlamaIndex, OpenAI, Azure OpenAI, Anthropic, Hugging Face, PostgreSQL, MySQL, Git, Docker, MLflow, AWS, Azure, GCP, CrewAI

Signals

Skill ml-engineer

0.52

Alias ai-engineer

1.00

KRA ai-compliance-officer

0.47

Post-classification

Centroidupdated · n=1

Alias collision log#6

New-role queue—

New skills captured0

New KRA capturedyes

Captured for admin review

R&R fragment (sim 0.00) ↔ AI Engineer pending

Status: extract_from_jd_done Created: 2026-05-18T22:54:45.257606Z Updated: 2026-05-18T22:54:46.007492Z

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

AI Engineer

Join us in building intelligent, AI-driven applications. We are looking for a hands-on AI Engineer with 2-3 years of experience excited about working with Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and conversational AI systems.

Responsibilities
- Design and build AI-powered applications and conversational agents using LLMs to interact with structured data sources
- Develop RAG pipelines using vector stores (Pinecone, FAISS, ChromaDB)
- Integrate frameworks like LangChain, LlamaIndex, CrewAI
- Work with OpenAI, Azure OpenAI, Anthropic, Hugging Face APIs
- Set up MLOps practices (model versioning, MLflow)

Required skills: Python, SQL, Snowflake, Pinecone, FAISS, ChromaDB, LangChain, LlamaIndex, OpenAI, Azure OpenAI, Anthropic, Hugging Face, PostgreSQL, MySQL, Git, Docker, MLflow, AWS, Azure, GCP, CrewAI

Skills from this JD

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

Python Primary 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)

Snowflake Primary No API 2 row (run stopped after API 1 or history missing)

Pinecone Primary No API 2 row (run stopped after API 1 or history missing)

FAISS Primary No API 2 row (run stopped after API 1 or history missing)

ChromaDB Primary No API 2 row (run stopped after API 1 or history missing)

LangChain Primary No API 2 row (run stopped after API 1 or history missing)

LlamaIndex Primary No API 2 row (run stopped after API 1 or history missing)

OpenAI Primary No API 2 row (run stopped after API 1 or history missing)

Azure OpenAI Primary No API 2 row (run stopped after API 1 or history missing)

Anthropic Primary No API 2 row (run stopped after API 1 or history missing)

Hugging Face Primary No API 2 row (run stopped after API 1 or history missing)

PostgreSQL Primary No API 2 row (run stopped after API 1 or history missing)

MySQL Primary No API 2 row (run stopped after API 1 or history missing)

Git Primary No API 2 row (run stopped after API 1 or history missing)

Docker Primary No API 2 row (run stopped after API 1 or history missing)

MLflow Primary No API 2 row (run stopped after API 1 or history missing)

AWS Primary No API 2 row (run stopped after API 1 or history missing)

Azure Primary No API 2 row (run stopped after API 1 or history missing)

GCP Primary No API 2 row (run stopped after API 1 or history missing)

CrewAI Primary 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

RoleAI Engineer

Experience2-3 years of experience

DomainOther

JD type pass

Show raw JSON

{
  "JD_type": "pass",
  "about_company": null,
  "certifications": [],
  "company_name": null,
  "ctc": null,
  "domain": {
    "primary": {
      "aliases": [],
      "domain": "Other"
    },
    "secondary": null
  },
  "education": [],
  "experience": {
    "max": 3,
    "min": 2,
    "raw": "2-3 years of experience"
  },
  "job_locations": [],
  "role": "AI Engineer",
  "role_archetype": "Engineering",
  "roles_and_responsibilities": [
    {
      "bullet_count": 5,
      "heading": "Responsibilities",
      "heading_was_present": true,
      "source_marker": {
        "first_5_words": "Responsibilities - Design and build",
        "last_5_words": "versioning, MLflow)"
      },
      "text": "- Design and build AI-powered applications and conversational agents using LLMs to interact with structured data sources\n- Develop RAG pipelines using vector stores (Pinecone, FAISS, ChromaDB)\n- Integrate frameworks like LangChain, LlamaIndex, CrewAI\n- Work with OpenAI, Azure OpenAI, Anthropic, Hugging Face APIs\n- Set up MLOps practices (model versioning, MLflow)",
      "word_count": 51
    },
    {
      "bullet_count": 0,
      "heading": "Required skills",
      "heading_was_present": true,
      "source_marker": {
        "first_5_words": "Required skills: Python, SQL,",
        "last_5_words": "AWS, Azure, GCP, CrewAI"
      },
      "text": "Python, SQL, Snowflake, Pinecone, FAISS, ChromaDB, LangChain, LlamaIndex, OpenAI, Azure OpenAI, Anthropic, Hugging Face, PostgreSQL, MySQL, Git, Docker, MLflow, AWS, Azure, GCP, CrewAI",
      "word_count": 30
    }
  ],
  "urls": []
}

API 1 — extract-from-jd click to toggle

{
  "final_skills": [
    {
      "is_primary": true,
      "skill_name": "Python"
    },
    {
      "is_primary": true,
      "skill_name": "SQL"
    },
    {
      "is_primary": true,
      "skill_name": "Snowflake"
    },
    {
      "is_primary": true,
      "skill_name": "Pinecone"
    },
    {
      "is_primary": true,
      "skill_name": "FAISS"
    },
    {
      "is_primary": true,
      "skill_name": "ChromaDB"
    },
    {
      "is_primary": true,
      "skill_name": "LangChain"
    },
    {
      "is_primary": true,
      "skill_name": "LlamaIndex"
    },
    {
      "is_primary": true,
      "skill_name": "OpenAI"
    },
    {
      "is_primary": true,
      "skill_name": "Azure OpenAI"
    },
    {
      "is_primary": true,
      "skill_name": "Anthropic"
    },
    {
      "is_primary": true,
      "skill_name": "Hugging Face"
    },
    {
      "is_primary": true,
      "skill_name": "PostgreSQL"
    },
    {
      "is_primary": true,
      "skill_name": "MySQL"
    },
    {
      "is_primary": true,
      "skill_name": "Git"
    },
    {
      "is_primary": true,
      "skill_name": "Docker"
    },
    {
      "is_primary": true,
      "skill_name": "MLflow"
    },
    {
      "is_primary": true,
      "skill_name": "AWS"
    },
    {
      "is_primary": true,
      "skill_name": "Azure"
    },
    {
      "is_primary": true,
      "skill_name": "GCP"
    },
    {
      "is_primary": true,
      "skill_name": "CrewAI"
    }
  ],
  "jd_role": {
    "display_name": "AI Engineer",
    "rationale": null,
    "role_archetype": "Engineering",
    "slug": ""
  },
  "nano_parsed": {
    "JD_type": "pass",
    "about_company": null,
    "certifications": [],
    "company_name": null,
    "ctc": null,
    "domain": {
      "primary": {
        "aliases": [],
        "domain": "Other"
      },
      "secondary": null
    },
    "education": [],
    "experience": {
      "max": 3,
      "min": 2,
      "raw": "2-3 years of experience"
    },
    "job_locations": [],
    "role": "AI Engineer",
    "role_archetype": "Engineering",
    "roles_and_responsibilities": [
      {
        "bullet_count": 5,
        "heading": "Responsibilities",
        "heading_was_present": true,
        "source_marker": {
          "first_5_words": "Responsibilities - Design and build",
          "last_5_words": "versioning, MLflow)"
        },
        "text": "- Design and build AI-powered applications and conversational agents using LLMs to interact with structured data sources\n- Develop RAG pipelines using vector stores (Pinecone, FAISS, ChromaDB)\n- Integrate frameworks like LangChain, LlamaIndex, CrewAI\n- Work with OpenAI, Azure OpenAI, Anthropic, Hugging Face APIs\n- Set up MLOps practices (model versioning, MLflow)",
        "word_count": 51
      },
      {
        "bullet_count": 0,
        "heading": "Required skills",
        "heading_was_present": true,
        "source_marker": {
          "first_5_words": "Required skills: Python, SQL,",
          "last_5_words": "AWS, Azure, GCP, CrewAI"
        },
        "text": "Python, SQL, Snowflake, Pinecone, FAISS, ChromaDB, LangChain, LlamaIndex, OpenAI, Azure OpenAI, Anthropic, Hugging Face, PostgreSQL, MySQL, Git, Docker, MLflow, AWS, Azure, GCP, CrewAI",
        "word_count": 30
      }
    ],
    "urls": []
  },
  "run_id": "830267ff-1c70-492f-84f3-48519722a847",
  "stage3_signals": {
    "alias_match_roles": [
      {
        "display_name": "AI Engineer",
        "matched_count": null,
        "role_id": 13,
        "score": 1.0,
        "slug": "ai-engineer",
        "total_count": null
      }
    ],
    "kra_match_roles": [
      {
        "display_name": "AI Compliance Officer",
        "matched_count": null,
        "role_id": 12,
        "score": 0.465,
        "slug": "ai-compliance-officer",
        "total_count": null
      },
      {
        "display_name": "ML Engineer",
        "matched_count": null,
        "role_id": 3,
        "score": 0.4388,
        "slug": "ml-engineer",
        "total_count": null
      },
      {
        "display_name": "Backend Engineer",
        "matched_count": null,
        "role_id": 1,
        "score": 0.436,
        "slug": "backend-engineer",
        "total_count": null
      },
      {
        "display_name": "Android Engineer",
        "matched_count": null,
        "role_id": 4,
        "score": 0.413,
        "slug": "android-engineer",
        "total_count": null
      },
      {
        "display_name": "AR/VR Engineer",
        "matched_count": null,
        "role_id": 8,
        "score": 0.4089,
        "slug": "ar-vr-engineer",
        "total_count": null
      }
    ],
    "skill_match_roles": [
      {
        "display_name": "ML Engineer",
        "matched_count": 11,
        "role_id": 3,
        "score": 0.5238,
        "slug": "ml-engineer",
        "total_count": 21
      },
      {
        "display_name": "Backend Engineer",
        "matched_count": 8,
        "role_id": 1,
        "score": 0.381,
        "slug": "backend-engineer",
        "total_count": 21
      },
      {
        "display_name": "Data Engineer",
        "matched_count": 7,
        "role_id": 2,
        "score": 0.3333,
        "slug": "data-engineer",
        "total_count": 21
      },
      {
        "display_name": "Cybersecurity Engineer",
        "matched_count": 5,
        "role_id": 5,
        "score": 0.2381,
        "slug": "cybersecurity-engineer",
        "total_count": 21
      },
      {
        "display_name": "DevOps Engineer",
        "matched_count": 5,
        "role_id": 10,
        "score": 0.2381,
        "slug": "devops-engineer",
        "total_count": 21
      }
    ],
    "stage35_ran": false
  },
  "stage4_decision": {
    "alias_collision_detected": true,
    "case": "D",
    "chosen_role": {
      "display_name": "AI Engineer",
      "matched_count": null,
      "role_id": 13,
      "score": 1.0,
      "slug": "ai-engineer",
      "total_count": null
    },
    "confidence": 0.92,
    "llm2_fired": true,
    "llm2_reasoning": "The JD\u2019s focus on building LLM-based applications, RAG pipelines, and integrating MLOps tools directly maps to the day-to-day responsibilities of an AI Engineer rather than a compliance-focused role.",
    "queued": false,
    "reasoning": "LLM2 picked ai-engineer (confidence 0.92)"
  },
  "stage5_updates": {
    "centroid_n_after": 1,
    "centroid_updated": true,
    "collision_log_id": 6,
    "new_kra_attached": {
      "best_kra_similarity": 0.0,
      "queue_id": 2,
      "r_and_r_preview": "- Design and build AI-powered applications and conversational agents using LLMs to interact with structured data sources\n- Develop RAG pipelines using vector stores (Pinecone, FAISS, ChromaDB)\n- Integ",
      "role_display_name": "AI Engineer",
      "role_slug": "ai-engineer",
      "status": "pending"
    },
    "new_skills_attached": [],
    "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…