Sr/Lead Genai Engineer

Epam Systems; Gurugram District; Hybrid; INR 1,800,000 - 3,200,000; Full time

Job summary

Epam Systems in Gurgaon is seeking an experienced Python AI Engineer to design production-grade Generative AI solutions with a focus on agentic workflows and multi-agent systems. You will work across product, engineering, and data teams to implement LLM-driven architectures.

The role requires strong Python skills, 3+ years with Generative AI/LLMs, and hands-on experience with agent frameworks, vector databases, and backend services. Join a collaborative, innovation-driven team in Gurgaon.

Qualifications

• 4-8 years of overall software engineering experience
• 3+ years of hands-on experience with Generative AI and LLMs
• Strong Python proficiency and production-ready application development
• Experience with at least two agentic AI frameworks (e.g., LangChain, LangGraph, Google ADK, CrewAI, AutoGen, or Copilot extensibility)
• Strong backend development skills including REST/gRPC APIs, asynchronous programming, Docker, FastAPI or Flask
• Strong familiarity with leading LLMs (OpenAI GPT, Claude, Gemini, etc.) and open-source options
• Experience building RAG solutions with vector databases (e.g., Pinecone, Weaviate, ChromaDB, Qdrant)
• Expertise in prompt engineering, LLM orchestration, guardrails, ReAct patterns, evaluation techniques
• Strong problem-solving, system design, and architectural decision-making
• Excellent communication across global teams

Responsibilities

• Design, architect, and develop scalable Generative AI applications and agentic solutions for real-world use cases
• Build and orchestrate AI agents using LangChain, LangGraph, Google ADK, CrewAI, AutoGen, Copilot Studio
• Develop and maintain backend services, APIs, microservices, and data pipelines powering AI-driven products
• Implement advanced AI patterns including RAG, Agentic RAG, tool calling, planning & reflection loops
• Engineer and optimize prompts, system instructions, and agent workflows for reliability and UX
• Integrate LLMs with enterprise systems, third-party APIs, vector databases, and knowledge repos
• Monitor and improve model/agent performance with observability tools and metrics
• Collaborate with Product, Engineering, Data, and Design teams to deliver AI solutions
• Stay current with emerging AI tech and contribute innovative ideas
• Document architectures and reusable patterns while supporting knowledge sharing

Skills

Python

LLM

Generative AI

Backend development

REST/gRPC APIs

Docker

FastAPI/Flask

System design

Problem solving

Communication

Tools

LangChain

LangGraph

Google ADK

CrewAI

AutoGen

Microsoft Copilot Studio

Kubernetes

Job description

Job Expectation

Role : Python.AI Engineer

Exp : 5 to10 Years

Location : Gurgaon

Role Overview

We are seeking an experienced AI Engineer to design and build production-grade Generative AI solutions with a strong focus on agentic workflows, multi-agent systems, and enterprise AI applications. The ideal candidate combines strong software engineering fundamentals with hands‑on expertise in LLMs, RAG architectures, and AI agent frameworks.

Key Responsibilities

• Design, architect, and develop scalable Generative AI applications and agentic solutions for real-world business use cases.
• Build and orchestrate AI agents using frameworks such as LangChain, LangGraph, Google ADK, CrewAI, AutoGen, Microsoft Copilot Studio, or similar technologies.
• Develop and maintain backend services, APIs, microservices, and data pipelines that power AI-driven products.
• Implement advanced AI patterns including RAG, Agentic RAG, tool/function calling, planning & reflection loops, and human-in-the-loop workflows.
• Engineer and optimize prompts, system instructions, and agent workflows to improve reliability, accuracy, and user experience.
• Integrate LLMs with enterprise systems, third‑party APIs, vector databases, and knowledge repositories.
• Monitor, evaluate, and continuously improve model and agent performance using observability tools, metrics, and user feedback.
• Collaborate closely with Product, Engineering, Data, and Design teams to deliver impactful AI solutions.
• Stay current with emerging AI technologies, frameworks, and best practices, contributing innovative ideas to the team.
• Document architectures, design decisions, and reusable solution patterns while supporting knowledge sharing across teams.

Required Qualifications

Must Have

• 4 -8 years of overall software engineering experience.
• 3+ years of hands‑on experience building applications using Generative AI and LLM technologies.
• Strong proficiency in Python and experience developing production-ready applications.
• Hands‑on experience with at least two agentic AI frameworks such as LangChain, LangGraph, Google ADK, CrewAI, AutoGen, or Microsoft Copilot extensibility.
• Strong backend development skills, including REST/gRPC APIs, asynchronous programming, Docker, and frameworks such as FastAPI or Flask.
• Solid understanding of leading LLMs including OpenAI GPT models, Anthropic Claude, Google Gemini, and open‑source alternatives.
• Practical experience building RAG solutions using vector databases such as Pinecone, Weaviate, ChromaDB, or Qdrant.
• Expertise in prompt engineering, LLM orchestration, structured outputs, guardrails, ReAct patterns, and evaluation techniques.
• Strong problem‑solving, system design, and architectural decision‑making skills.
• Excellent communication skills with the ability to collaborate effectively across global teams.

Preferred Qualifications

• Experience with AI observability and evaluation tools such as LangSmith, Ragas, DeepEval, Arize, or Weights & Biases.
• Familiarity with model adaptation and fine‑tuning techniques (LoRA, PEFT, RLHF concepts).
• Experience with cloud AI platforms including Azure OpenAI, AWS Bedrock, or Google Vertex AI.
• Understanding of CI/CD, MLOps, and LLMOps practices.
• Exposure to graph databases, knowledge graphs, and structured data integration.
• Experience with event‑driven architectures and messaging platforms such as Kafka or RabbitMQ.