Job Title:
Generative AI Platform Engineer (LLM Ops, Python, Vector DB, RAG)
Company: Tata Consultancy Services
Location: Pune, Maharashtra
Created: 2026-01-14
Job Type: Full Time
Job Description:
TCS Hiring !!.Generative AI Platform Engineer (LLM Ops, Python, Vector DB, RAG)Please read Job description before ApplyingSKILLS: Generative AI Platform Engineer (LLM Ops, Python, Vector DB, RAG)petencies (Technical/Behavioral Competency)Must-Have**(Ideally should not bemore than 3-5) · LLM Ops: Experience with prompt engineering, prompt/version management, routing across models, and LLM evaluation. · RAG Expertise: Practical experience building and tuning RAG pipelines (chunking strategies, embeddings, retrievers, reranking). · Vector DBs: Hands-on with at least one: FAISS, Pinecone, Milvus, Weaviate (index types, parameters, scaling). · Python Engineering: Strong Python with FastAPI/Flask, async IO, typing, packaging; clean code & SOLID principles. · MLOps/Platform: Docker, Kubernetes, Git, CI/CD (Jenkins/GitHub Actions/Azure DevOps), observability (logs/metrics/traces). · APIs: Design/consume REST APIs, OpenAPI/Swagger, pagination, error models, rate limiting. · Data Handling: Experience with text preprocessing, embeddings, metadata schemas, and storage (object stores/RDBMS). · Build production-grade RAG pipelines, manage vector databases, and own LLM Ops—including observability, evaluation, and cost/performance optimization—on secure, compliant platforms.NOTE: If the skills/profile matches and interested, please reply to this email by attaching your latest updated CV and with below few details:Name:Contact Number:Email ID:Highest Qualification in: (Eg. B.Tech/B.E./M.Tech/MCA/M.Sc./MS/BCA/B.Sc./Etc.)Current Organization Name:Total IT Experience-7+ yearsLocation: TCS: HyderabadCurrent CTCExpected CTCNotice period: Immediate JoinerWhether worked with TCS - Y/NRetrieval & Ranking: BM25, hybrid search, approximate nearest neighbor configs, rerankers (e.g., cross-encoders). · Model Ecosystem: Experience with OpenAI, Azure OpenAI, Anthropic, Cohere, local models (Llama, Mistral) and serving frameworks (vLLM/Triton).