GenAI / LLM Engineer (RAG Production)

Role: GenAI / LLM Engineer

Experience: 510 Years

Location: Bangalore / Pune / Hyderabad / Chennai

Notice Period: Immediate to 45 Days

Job Summary

We are looking for an experienced GenAI / LLM Engineer with strong hands-on expertise in building and deploying production-grade RAG (Retrieval-Augmented Generation) applications. The ideal candidate should have experience with LLMs, LangChain, LangGraph, FastAPI, Hugging Face, Vector Databases, and Machine Learning, along with deploying scalable AI solutions.

Key Responsibilities

- Design, develop, and deploy production-ready RAG applications using Large Language Models (LLMs).
- Build AI workflows using LangChain and LangGraph for agentic AI and multi-agent systems.
- Integrate and optimize LLMs such as OpenAI, Llama, Mistral, Claude, Gemini, etc.
- Develop REST APIs using FastAPI for AI/ML services.
- Implement document ingestion, chunking, embedding generation, indexing, and retrieval pipelines.
- Work with Vector Databases to enable semantic search and efficient retrieval.
- Fine-tune and deploy open-source models using Hugging Face Transformers.
- Apply Machine Learning techniques for model evaluation, optimization, and inference.
- Optimize prompt engineering, context management, and response quality.
- Deploy scalable AI services on cloud platforms (AWS, Azure, or GCP).
- Collaborate with Data Engineers, ML Engineers, and Product teams to deliver AI-powered applications.

Required Skills
- Strong experience with Production-grade RAG implementations.
- Hands-on experience with Large Language Models (LLMs).
- Strong expertise in LangChain and LangGraph.




- Experience with Machine Learning fundamentals and model deployment.
- Hands-on experience with FastAPI.
- Experience with Hugging Face (Transformers, Pipelines, Fine-tuning).
- Experience with Vector Databases, such as:
- Knowledge of embedding models and semantic search.
- Strong programming skills in Python.
- Experience with REST APIs and microservices.
- Good understanding of Git, Docker, and CI/CD pipelines.

Good to Have
- Experience with Azure OpenAI, Azure AI Foundry, or AWS Bedrock.
- Knowledge of LlamaIndex.
- Experience with AI Agents and Agentic AI architectures.
- Familiarity with Kubernetes and container orchestration.
- Experience with monitoring and evaluating LLM applications (LangSmith, MLflow, Promptflow, etc.).

Qualifications
- Bachelor's or Master's degree in Computer Science, AI/ML, Data Science, or a related field.
- 510 years of software development experience with at least 2+ years of hands-on GenAI/LLM experience.
- environments.

Mandatory Skills
- Python
- Machine Learning
- Large Language Models (LLMs)
- Production RAG
- LangChain
- LangGraph
- FastAPI
- Hugging Face Transformers
- Vector Databases (Pinecone, FAISS, ChromaDB, Milvus, Weaviate, Qdrant, Azure AI Search)
- TorchServe / TensorFlow Serving
- Docker
- Kubernetes
- REST APIs
- Git & CI/CD

Valuable to Have
- Azure OpenAI / Azure AI Foundry / AWS Bedrock
- LlamaIndex
- Prompt Engineering
- AI Agents / Agentic AI
- MLflow, LangSmith, Promptflow
- Redis, Kafka
- PostgreSQL / MongoDB
- Cloud Platforms: AWS, Azure, or GCP

This combination is well-suited for hiring Senior GenAI / AI Platform Engineers with end-to-end experience building, deploying, and maintaining production-grade LLM and RAG applications.

Colour for this NVite

📌 Data Scientist (Bengaluru)
🏢 EPAM Systems
📍 Bengaluru