Job highlights

- Experience with Python, Large Language Models, Retrieval-Augmented Generation, Agentic AI, prompt engineering, and frameworks like LangChain or LlamaIndex

- Design, develop, and deploy Generative AI and LLM-powered applications; build RAG pipelines; develop Agentic AI solutions; integrate LLMs with enterprise systems; implement prompt engineering and backend APIs; ensure production readiness and collaborate across teams

: Generative AI Engineer

Job Summary

We are looking for a Generative AI Engineer with strong hands-on experience in Python, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), Agentic AI, and prompt engineering. The candidate will be responsible for designing, developing, and deploying scalable GenAI solutions for enterprise use cases.

Key Responsibilities

- Design and develop Generative AI and LLM-powered applications using Python.

- Build end-to-end RAG pipelines, including document ingestion, chunking, embeddings, retrieval, reranking, and response generation.

- Develop Agentic AI solutions involving tool calling, planning, memory, workflow orchestration, and multi-agent systems.

- Integrate LLMs with enterprise applications, APIs, databases, and knowledge repositories.

- Develop solutions using LangChain, LangGraph, LlamaIndex, or similar frameworks.

- Work with vector databases such as FAISS, Pinecone, ChromaDB,



Weaviate, or Qdrant.

- Implement prompt engineering, structured outputs, function/tool calling, and context management.

- Develop APIs and backend services using FastAPI or Flask.

- Evaluate GenAI systems for accuracy, relevance, hallucination, latency, reliability, and cost.

- Implement guardrails, security, logging, tracing, and monitoring for production GenAI applications.

- Collaborate with engineering, data science, cloud, and business teams to take GenAI solutions from PoC to production.

Mandatory Skills

- Strong programming experience in Python

- Solid understanding of Generative AI and LLMs

- Hands-on experience with RAG

- Hands-on experience with Agentic AI / AI Agents

- LangChain / LangGraph / LlamaIndex

- Prompt Engineering

- Embeddings and Semantic Search

- Vector Databases

- REST API development using FastAPI / Flask

- Git and Docker

- Experience integrating LLM APIs and AI services

Good to Have

- Azure OpenAI / Azure AI Foundry

- AWS Bedrock / Google Vertex AI

- Open-source models such as Llama, Mistral, or Hugging Face models

- LLMOps / MLOps

- RAGAS, LangSmith, Langfuse, or similar evaluation/observability tools

- Kubernetes and CI/CD

- Fine-tuning / PEFT techniques

- Responsible AI, guardrails, and PII/security controls

📌 Gen AI Engineer (Chennai)
🏢 HCLTech
📍 Chennai