Senior AI/ML Engineer — Enterprise AI Framework

Experience: 4–8 Years

Role Type: Full-time

Primary Area: Applied AI / Generative AI / RAG Engineering

Project: Enterprise AI Framework (EAF)

Role Summary

Senior AI/ML Engineer to design, build, evaluate and mature the intelligence layer of our Enterprise AI Framework.

The role focuses primarily on production-grade Retrieval-Augmented Generation (RAG), retrieval quality, embeddings, reranking, context engineering, LLM integration, guardrails and AI evaluation.

This is not a prompt-engineering-only role and it is not primarily a model-training/research role.

The engineer must understand how to build reliable AI systems in which responses are grounded in governed enterprise evidence and important business decisions remain deterministic, auditable and human-controlled.

Key Responsibilities

- Design and improve production RAG/retrieval pipelines.
- Develop semantic, keyword and hybrid retrieval strategies.
- Tune chunking, embeddings, metadata filters, top-K selection and reranking.
- Diagnose retrieval failures and improve Recall@K, MRR, precision and related quality measures.
- Design evidence-aware context assembly and context prioritization.
- Prevent irrelevant/context-overloaded prompts.
- Develop and maintain LLM gateway/model abstraction components.
- Integrate commercial or open-source LLMs through controlled interfaces.
- Implement model timeout, retry, fallback, cost and token controls.
- Develop versioned system prompts and structured output contracts.
- Build AI guardrails for grounding, citations, unsupported claims, PII and policy constraints.




- Work with deterministic business logic and scoring engines without transferring decision authority to an LLM.
- Design evaluation datasets/golden sets.
- Build automated retrieval, prompt and model regression tests.
- Establish trustworthy offline and online AI-quality measurement.
- Investigate hallucination, retrieval drift and context-quality failures.
- Evaluate and integrate rerankers/cross-encoders where justified.
- Work with local and hosted embedding models.
- Contribute to graph-assisted retrieval/entity-aware context where quality evidence justifies it.
- Support future proactive/agentic workflows while maintaining bounded actions and human accountability.
- Instrument AI components for quality, latency, tokens, cost and guardrail outcomes.
- Work with Data Engineering to ensure ingestion/indexing quality and with Backend Engineering for APIs/orchestration/security.
- Conduct architecture/design reviews and mentor less-experienced AI engineers.

Must-Have SkillsApplied AI / ML Engineering

- 4–8 years overall engineering/AI/ML experience with substantial hands-on software development.
- Strong Python programming.
- Solid machine-learning fundamentals.
- Hands-on production experience with LLM/Generative AI applications.
- Strong understanding of Retrieval-Augmented Generation.
- Experience with embeddings and semantic search.
- Experience with vector databases/search platforms.




- Strong understanding of document chunking and retrieval design.
- Experience integrating LLM APIs.
- Prompt/context engineering.
- Automated evaluation/testing experience.
- Ability to interpret retrieval and ranking metrics.
- Strong debugging and system-design ability.

RAG / Search Depth

Candidate should understand

- semantic retrieval;
- keyword retrieval;
- hybrid search;
- metadata filtering;
- embeddings;
- top-K;
- reranking;
- cross-encoders;
- context assembly;
- grounding;
- hallucination;
- citations;
- retrieval evaluation.

Equivalent technology experience is acceptable.

Strongly Preferred

- Qdrant, pgvector, Pinecone, Weaviate, Milvus or similar.
- BM25/hybrid retrieval.
- Cross-encoder reranking.
- sentence-transformers.
- Claude, OpenAI or equivalent LLM APIs.
- RAG evaluation frameworks.
- Promptfoo or similar regression tooling.
- RAGAS or equivalent evaluation methodology.
- PII/guardrail implementations.
- Structured LLM outputs / JSON Schema.
- OpenTelemetry.
- Production AI observability.
- Knowledge graph / GraphRAG concepts.
- Entity-aware retrieval.

Nice to Have

- Neo4j or graph databases.
- LangChain, LlamaIndex, LangGraph or equivalent.
- Model gateways such as LiteLLM.
- MLflow / Weights & Biases.
- AWS AI infrastructure.
- Prompt-injection/adversarial testing.
- AI security and governance.
- Agentic workflow design.
- Fine-tuning experience.

Fine-tuning experience is useful but not a core requirement for the current EAF role Pay: ₹100,000.00 - ₹200,000.00 per month

Advantages

- Life insurance
- Provident Fund

Work Location: In person

📌 Sr.AI/ML Engineer (Coimbatore)
🏢 G2 Technology Solutions India
📍 Coimbatore