Gen AI Engineer

HCLTech; Bengaluru; On-site; INR 4,000,000 - 7,000,000; Full time

Job summary

HCL Technologies Limited in Bengaluru seeks a seasoned Generative AI Engineer with 5–10 years of hands-on experience in Python, LLMs, RAG, and Agentic AI to design and productionize enterprise GenAI solutions.

You will build scalable GenAI applications, implement end-to-end RAG pipelines, tool-calling agents, and integration with enterprise APIs, databases, and knowledge bases, collaborating with product and platform teams.

Qualifications

• Hands-on experience with Generative AI and LLMs architecture.
• Experience building RAG applications and end-to-end pipelines.
• Strong programming skills in Python and API development.

Responsibilities

• Design and develop scalable GenAI and LLM-based applications.
• Build end-to-end RAG pipelines including ingestion, embeddings, indexing and retrieval.
• Develop Agentic AI workflows with tool-calling and memory features.
• Implement advanced retrieval techniques and hybrid retrieval patterns.
• Integrate LLMs with enterprise apps, APIs, databases, and knowledge bases.
• Develop backend services and REST APIs using FastAPI/Flask.
• Apply prompt engineering, structured outputs, and function/tool calling.
• Evaluate GenAI solutions for accuracy, latency, and cost.
• Implement logging, monitoring, and security for production GenAI apps.
• Collaborate with product, engineering, research, and platform teams to deliver end-to-end GenAI solutions.

Skills

Python

GenAI

LLM Architecture

RAG

Agentic AI

Tools

FastAPI

Flask

Job description

We are looking for a skilled Generative AI Engineer with 5 to 10 years strong hands-on expertise in Python, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Agentic AI.

The candidate will design, develop, and productionize enterprise-grade GenAI applications, including conversational AI, knowledge assistants, intelligent agents, and multi-step AI workflows.

Key Responsibilities

• Design and develop scalable Generative AI and LLM-based applications using Python.
• Build end-to-end RAG pipelines, covering document ingestion, text preprocessing, chunking, embeddings, vector indexing, retrieval, prompt construction, and LLM response generation.
• Develop Agentic AI workflows, including tool-calling agents, stateful agents, conditional routing, memory, and multi-agent orchestration.
• Implement advanced retrieval techniques such as semantic search, metadata filtering, hybrid retrieval, and reranking to improve response relevance. These patterns also appear in internally shared GenAI profiles.
• Integrate LLMs with enterprise applications, APIs, databases, knowledge repositories, and external tools.
• Develop backend services and REST APIs using FastAPI/Flask.
• Implement prompt engineering, structured outputs, function/tool calling, and context-management techniques.
• Evaluate RAG and LLM solutions for accuracy, relevance, hallucination, latency, reliability, and cost.
• Implement logging, tracing, monitoring, exception handling, security, and observability for production GenAI applications.
• Work with product, engineering, research, and platform teams to deliver GenAI solutions end-to-end.

Mandatory Skills

• Strong hands-on programming experience in Python
• Strong understanding of Generative AI and LLM architecture
• Hands-on experience building RAG applications