Role Purpose

Deliver the natural-language query capability over the Entity Graph. This role implements the vector indexing and retrieval layer that powers GraphRAG — enabling users to ask questions in plain language instead of writing graph queries — and is accountable for the accuracy, relevance and evaluation of those responses.

Key Responsibilities

- Vector index design & build — design and implement the vector indexing strategy over graph projections and entity attributes, including chunking, embedding selection and index configuration.
- Embedding pipeline — build pipelines to generate, store and refresh embeddings as entity and graph data changes.
- GraphRAG implementation — combine vector similarity search with graph structure and multi-hop traversal to produce grounded, context-rich retrieval.
- Natural-language query enablement — implement and tune NLQ scenarios agreed with WK; support natural-language-to-graph-query translation approaches.
- Retrieval evaluation & tuning — define and run evaluation harnesses measuring retrieval relevance and answer quality; tune retrieval parameters against agreed scenarios.
- Grounding & traceability — ensure retrieved answers are attributable to source entities and edges, preserving provenance.
- Performance & cost management — optimise index size, query latency and compute/token cost of retrieval operations.
- Documentation — document retrieval architecture, evaluation results, known limitations and supported query patterns.

Required Skills & Experience

Skill Area

Specific Requirements

Vector Search

Vector databases and indexes (Azure AI Search, FAISS, pgvector, Pinecone, Milvus or Fabric vector capabilities); ANN indexing, similarity metrics

Embeddings

Embedding model selection and evaluation, chunking strategies, embedding refresh and drift handling

RAG / GraphRAG





Retrieval-augmented generation patterns, graph-aware retrieval, context assembly, grounding and citation

AI / LLM

Azure OpenAI or equivalent, prompt design for retrieval, natural-language-to-query translation

Engineering

Python, PySpark, SQL, API development, pipeline orchestration

Evaluation

Retrieval relevance metrics, evaluation harness design, A/B tuning, hallucination and grounding checks

Platform

Microsoft Fabric, Azure AI services, OneLake

Must-Have Qualifications

- 5+ years engineering experience with 2+ years hands-on vector search / RAG implementation
- Demonstrable production experience building a retrieval pipeline (not prototype-only)
- Strong Python skills and familiarity with embedding models
- Experience evaluating and tuning retrieval quality with defined metrics
- Understanding of how to ground responses and preserve source traceability

Nice-to-Have
- Direct GraphRAG experience (graph + vector combined retrieval)
- Familiarity with Microsoft Fabric NL2GQL / Data Agent capabilities
- Exposure to graph databases and traversal concepts
- Experience managing LLM inference cost and latency at scale

Key Deliverables Owned
- Vector index over graph projections
- Embedding generation and refresh pipeline
- GraphRAG retrieval capability supporting agreed NLQ scenarios
- Retrieval evaluation results and tuning documentation
- Documented supported query patterns and known limitations

Dual Role / Complementary Skills Strongly complementary with the Sr. GraphDB Engineer (Role 3) — GraphRAG is inherently graph plus vector. Because the vector workload concentrates in Phase 2, this role is a robust candidate for consolidation with Role 3 into a single Graph & Vector Engineer if headcount optimisation is required. During Phase 1 this role can contribute to unstructured/document processing and entity attribute enrichment.

📌 Vector DB Engineer (Gurugram)
🏢 EXL
📍 Gurugram