Gen AI Engineer / Senior Gen AI Engineer
Job Opening: Gen AI Engineer / Senior Gen AI Engineer
Experience-3-8 years
Location: Chennai, Hyderabad,Bangalore, Pune ,Kolkata and Noida
About the Role
- As a Gen AI Engineer / Senior Gen AI Engineer, you will drive the end-to-end architecture, development, and operationalization of production-ready Generative AI solutions. This role goes beyond proof-of-concept experimentation—you will be responsible for building robust, scalable Retrieval-Augmented Generation (RAG) pipelines, adapting and fine-tuning models for domain-specific requirements, and seamlessly embedding generative capabilities into mission-critical enterprise systems.
Core Responsibilities
LLM Architecture & Orchestration: Build, evaluate, and maintain modular LLM workflows using frameworks such as LangChain, LlamaIndex, or Semantic Kernel.
Retrieval-Augmented Generation (RAG): Design and tune scalable RAG pipelines using vector storage and search engines (Pinecone, FAISS, Weaviate, or Azure AI Search).
Model Adaptation & Tuning: Fine-tune both open-weight and proprietary foundation models to optimize domain accuracy, inference latency, and computational costs.
API & Service Development: Build asynchronous, high-throughput microservices using FastAPI, containerize via Docker, and deploy across cloud environments (Azure Functions / AWS) for low-latency production serving.
Enterprise Solutions: Architect and scale commercial AI products, autonomous copilots, and structured content automation tools utilizing OpenAI, Azure OpenAI, and Hugging Face ecosystems.
Prompt Engineering & Tool Use: Establish systematic prompt versioning, structured output parsing, and dynamic context-routing workflows to ensure deterministic performance.
Quality, Evaluation & Observability: Implement automated evaluation suites using frameworks like RAGAS or TruLens to monitor hallucination frequency, retrieval relevance, token drift, and answer faithfulness in real time.
POC to Production Lifecycle: Partner with engineering, data, and product teams to translate enterprise challenges into production-ready AI services with clear operational SLAs.
Engineering Rigor & Governance: Establish development standards for model routing, guardrails, context management, and responsible AI practices.
Required Qualifications & Experience
Total Experience: 3 to 6 years of core software engineering and system design experience.
Specialized GenAI Experience: Minimum of 2 years dedicated to shipping LLM-powered applications, GenAI workflows, and document/OCR processing pipelines to production.
Core Language: Strong command of Python, specifically modern async paradigms (asyncio), strict type annotations, object-oriented design, and maintainable software architecture.
Model Ecosystem: Practical experience integrating both proprietary endpoints (GPT-4o, Claude, Azure OpenAI) and open-weights (Llama 3, Mistral), alongside modern agentic design patterns.
Retrieval & Vector Search: Hands-on expertise implementing hybrid search (dense semantic + sparse BM25/lexical), re-ranking strategies (cross-encoders), metadata partitioning, and index optimization.
Deployment & Cloud Infrastructure: Solid foundation in containerization (Docker), API framework design (FastAPI), CI/CD release automation, and cloud services (Azure or AWS).
Engineering Problem Solving: Demonstrated capability in resolving real-world GenAI hurdles, including hallucination mitigation, context-window compression/budgeting, and data grounding verification.