Sr/Lead - Gen AI Engineer

Epam Systems; Puducherry, Chennai District, Cuddalore; Hybrid; INR 1,500,000 - 2,100,000; Full time

Job summary

Epam Systems in Chennai is seeking a Senior/Lead Generative AI Engineer to architect end-to-end AI solutions, focusing on LLMs, NLP, RAG, and agentic systems.

You will design and optimize RAG pipelines with vector stores (FAISS, Pinecone, Weaviate, Chroma), build scalable APIs, and fine-tune models to meet domain goals.

The role requires hands-on Python expertise, GenAI libraries, cloud/MLOps experience, and collaboration across product and engineering teams in a hybrid setup.

Responsibilities

• Design, develop, and optimize Generative AI applications using LLMs (OpenAI, Mistral, LLaMA, Claude, etc.).
• Architect and implement RAG pipelines combining LLMs with vector stores (e.g., FAISS, Pinecone, Weaviate, Chroma).
• Develop and orchestrate agentic workflows using frameworks like LangGraph, AutoGen, or CrewAI.
• Integrate AI models with structured and unstructured data sources for advanced NLP tasks such as summarization, semantic search, chatbots, and document intelligence.
• Build scalable APIs and services around LLMs and RAG pipelines.
• Fine-tune or prompt-engineer foundation models to meet domain-specific objectives.
• Collaborate with cross-functional teams including product managers, MLOps, and frontend developers.
• Stay up to date with advancements in generative AI research and tools.

Job description

Experience: 5 - 10 Years

Location: Chennai

Employment Type: Full-time

Work Mode - Hybrid

Role Summary:

We are seeking a Senior/Lead Generative AI Engineer with strong hands-on experience in LLMs, Natural Language Processing (NLP), Retrieval-Augmented Generation (RAG), and Agentic AI systems. The ideal candidate will be responsible for building and optimizing end-to-end generative AI solutions, integrating with vector databases, and designing intelligent agentic systems to drive real-world business impact.

Key Responsibilities:

• Design, develop, and optimize Generative AI applications using LLMs (OpenAI, Mistral, LLaMA, Claude, etc.).
• Architect and implement RAG pipelines combining LLMs with vector stores (e.g., FAISS, Pinecone, Weaviate, Chroma).
• Develop and orchestrate agentic workflows using frameworks like LangGraph, AutoGen, or CrewAI.
• Integrate AI models with structured and unstructured data sources for advanced NLP tasks such as summarization, semantic search, chatbots, and document intelligence.
• Build scalable APIs and services around LLMs and RAG pipelines.
• Fine-tune or prompt-engineer foundation models to meet domain-specific objectives.
• Collaborate with cross-functional teams including product managers, MLOps, and frontend developers.
• Stay up to date with advancements in generative AI research and tools.

Required Skills:

• 58 years of experience in AI/ML with at least 2+ years in GenAI/LLMs/NLP.
• Strong expertise in Python and GenAI libraries (e.g., LangChain, Transformers, LLamaIndex, Haystack).
• Hands-on experience building RAG-based applications and working with vector databases.
• Familiarity with agentic frameworks (LangGraph, AutoGen, CrewAI, etc.).
• Experience in prompt engineering, model fine-tuning, and evaluation.
• Solid understanding of NLP pipelines, tokenization, embeddings, and text analytics.
• Experience with cloud platforms (AWS, Azure, GCP) and MLOps pipelines.
• Strong problem-solving skills and ability to drive projects independently.

CTC :

Exp CTC:

Notice :

Available for F2F Interview Chennai office on 29th Aug (Y/N) :