Python AI Engineer

Epam Systems; Hyderabad, Gurugram District, Bengaluru; On-site; INR 2,500,000 - 4,500,000; Full time

Job summary

Epam Systems in Hyderabad is seeking an AI Engineer to design, develop, and deploy scalable AI agents and Generative AI solutions. You will build multi-agent systems, RAG-based apps, and REST APIs with FastAPI, while integrating with enterprise tools and cloud platforms.

The ideal candidate has 5+ years of software experience in Python, strong knowledge of agentic AI frameworks, and hands-on work with vector databases and LLMs.

Qualifications

• 5+ years of software development experience with Python.
• Experience building AI-powered applications with LLMs.
• Hands-on experience with multi-agent systems and RAG.

Responsibilities

• Design and develop AI-powered applications using Python and modern Generative AI frameworks.
• Build single-agent and multi-agent AI systems for enterprise use cases.
• Develop scalable RAG solutions using vector databases and LLMs.
• Build REST APIs and backend services using FastAPI.
• Integrate AI applications with external tools, APIs, databases, and enterprise systems.
• Optimize LLM performance through prompt engineering, evaluation, monitoring, and observability.
• Collaborate with cross-functional teams to deliver secure, scalable, and production-ready AI solutions.
• Follow best practices for testing, deployment, security, and Responsible AI.

Skills

Python

LangGraph

LangChain

CrewAI

AutoGen

LLMs

Prompt engineering

Tool calling

Memory

Agent orchestration

RAG

Vector DBs

Pinecone

Chroma

Weaviate

Qdrant

FastAPI

REST API

MCP

Git

Docker

CI/CD

Production deployment

Debugging

Security

Responsible AI

Tools

FastAPI

Kubernetes

CI/CD tooling

Job description

About the Role

We are looking for a passionate AI Engineer with strong expertise in Python and Agentic AI to build next-generation intelligent applications powered by Large Language Models (LLMs). You will design, develop, and deploy scalable AI agents, multi-agent systems, and production-grade Generative AI solutions using modern AI frameworks and cloud platforms.

Key Responsibilities

• Design and develop AI-powered applications using Python and modern Generative AI frameworks.
• Build and deploy single-agent and multi-agent AI systems for enterprise use cases.
• Develop scalable RAG (Retrieval-Augmented Generation) solutions using vector databases and LLMs.
• Build REST APIs and backend services using FastAPI.
• Integrate AI applications with external tools, APIs, databases, and enterprise systems.
• Optimize LLM performance through prompt engineering, evaluation, monitoring, and observability.
• Collaborate with cross-functional teams to deliver secure, scalable, and production-ready AI solutions.
• Follow best practices for testing, deployment, security, and Responsible AI.

Required Skills

• 5+ years of software development experience with strong proficiency in Python.
• Hands‑on experience with LangGraph, LangChain, CrewAI, AutoGen, or similar agentic AI frameworks.
• Strong understanding of LLMs, prompt engineering, tool calling, memory, and multi‑agent orchestration.
• Experience building RAG applications using vector databases such as Pinecone, Chroma, Weaviate, or Qdrant.
• Hands‑on experience with FastAPI and REST API development.
• Knowledge of Model Context Protocol (MCP) or similar agent communication frameworks.
• Experience with Git, Docker, CI/CD, and production deployment.
• Strong problem‑solving and debugging skills.

Good to Have

Experience with one or more cloud AI platforms:

• Google Cloud: Vertex AI, Gemini, Google ADK
• Microsoft Azure: Azure OpenAI, Azure AI Foundry, Azure AI Search
• AWS: Amazon Bedrock, Bedrock Agents, AgentCore

Additional exposure to:

• Semantic Kernel
• LlamaIndex
• OpenTelemetry
• LangSmith or Langfuse
• Kubernetes
• MLOps and AI observability

What We're Looking For

• Strong understanding of AI agent architecture and LLM application development.
• Ability to build scalable, production-ready AI solutions.