Sr/Lead Genai Engineer

Epam Systems; Indore District; Hybrid; INR 3,000,000 - 5,000,000; Full time

Job summary

Epam Systems is seeking an experienced Sr/Python engineer to lead design and development of production-grade Generative AI and Agentic AI solutions for enterprise use cases in Indore, India. The role focuses on Python, LLMs, RAG, multi-agent architectures, and building scalable AI-driven data pipelines.

You will guide engineering teams, implement agentic workflows, and integrate with enterprise systems using REST/gRPC APIs and modern frameworks.

Qualifications

• 5 to 12 years of software engineering experience.
• 3+ years building Generative AI/LLM-based applications.
• Strong expertise in Python and production-grade software development.
• Hands-on with Agentic AI frameworks such as LangChain, LangGraph, Google ADK, CrewAI, AutoGen, or Copilot extensibility.
• Backend development with FastAPI/Flask, REST/gRPC APIs, asynchronous programming, Docker, and microservices.
• Broad understanding of LLMs including OpenAI GPT, Claude, Gemini, and open-source models.
• Experience designing RAG and Agentic RAG architectures.
• Familiarity with vector databases like Pinecone, Weaviate, ChromaDB, or Qdrant.
• Knowledge of prompt engineering, tool calling, structured outputs, and guardrails.
• System design, distributed systems, API architecture, and cloud-native development.
• Ability to provide technical leadership and mentoring.

Responsibilities

• Lead design, development, and delivery of scalable GenAI and agentic apps.
• Design and implement AI agents, multi-agent systems, and agentic workflows.
• Build and orchestrate agents using LangChain, LangGraph, Google ADK, CrewAI, AutoGen, Copilot extensibility.
• Develop production-grade Python applications, backend services, and AI-driven data pipelines.
• Implement GenAI patterns including RAG, Agentic RAG, tool calling, ReAct, memory, and human-in-the-loop workflows.
• Design prompts, system instructions, structured outputs, guardrails, and evaluation mechanisms.
• Integrate LLMs with enterprise apps, APIs, vector databases, and data stores.
• Work with models like OpenAI GPT, Claude, Gemini, and open-source LLMs.
• Lead scalable RAG solutions using Pinecone, Weaviate, ChromaDB, Qdrant, or equivalents.
• Provide technical leadership, code reviews, and mentoring to engineers.
• Collaborate with Product, Engineering, Data, Cloud, and Architecture teams.
• Establish reusable patterns and best practices for GenAI engineering.
• Contribute to architecture decisions, docs, and innovation initiatives.

Skills

Python programming

Distributed systems

Problem solving

Mentoring

Communication

Team collaboration

Tools

LangChain

LangGraph

Google ADK

CrewAI

AutoGen

Copilot extensibility

Docker

REST APIs

gRPC

Pinecone

Weaviate

ChromaDB

Qdrant

LangSmith

Arize

Job description

We are looking for an experienced Sr/Python with design and development of production-grade Generative AI and Agentic AI solutions for enterprise use cases. The ideal candidate will have strong Python and software engineering fundamentals, hands-on experience with LLMs, RAG, AI agents, and multi-agent architectures, along with the ability to technically guide engineering teams.

Key Responsibilities:

• - Lead the design, development, and delivery of scalable Generative AI and Agentic AI applications.
• - Design and implement AI agents, multi-agent systems, and agentic workflows for complex enterprise use cases.
• - Build and orchestrate agents using frameworks such as LangChain, LangGraph, Google ADK, CrewAI, AutoGen, Microsoft Copilot extensibility, or similar frameworks.
• - Develop production-grade Python applications, backend services, REST/gRPC APIs, microservices, and AI-driven data pipelines.
• - Implement advanced GenAI patterns including RAG, Agentic RAG, tool/function calling, ReAct, planning, reflection, memory, and human-in-the-loop workflows.
• - Design prompt strategies, system instructions, structured outputs, guardrails, and evaluation mechanisms to improve LLM reliability and accuracy.
• - Integrate LLMs with enterprise applications, APIs, vector databases, knowledge repositories, and external tools.
• - Work with models such as OpenAI GPT, Anthropic Claude, Google Gemini, and open-source LLMs.
• - Lead the development of scalable RAG solutions using Pinecone, Weaviate, ChromaDB, Qdrant, or equivalent vector databases.
• - Implement AI observability, evaluation, monitoring, and continuous improvement using tools such as LangSmith, Ragas, DeepEval, Arize, or Weights & Biases.
• - Provide technical leadership, code reviews, mentoring, and guidance to engineers working on GenAI solutions.
• - Collaborate with Product, Engineering, Data, Cloud, and Architecture teams to translate business requirements into technical solutions.
• - Establish reusable design patterns, development standards, and best practices for GenAI engineering.
• - Contribute to technical documentation, architecture decisions, proof of concepts, and innovation initiatives.
• - Stay current with emerging Agentic AI, LLM, GenAI frameworks, models, and enterprise AI technologies.

Required Qualifications :

Must Have :

• - 5 to 12 years of overall software engineering experience.
• - 3+ years of hands-on experience building Generative AI/LLM-based applications.
• - Strong expertise in Python and production-grade software development.
• - 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 experience with FastAPI/Flask, REST/gRPC APIs, asynchronous programming, Docker, and microservices.
• - Strong understanding of LLMs including OpenAI GPT, Anthropic Claude, Google Gemini, and open-source models.
• - Hands-on experience designing and implementing RAG and Agentic RAG architectures.
• - Experience with vector databases such as Pinecone, Weaviate, ChromaDB, or Qdrant.
• - Strong knowledge of prompt engineering, tool/function calling, structured outputs, guardrails, ReAct, memory, and LLM evaluation.
• - Strong understanding of system design, distributed systems, API architecture, and cloud-native development.
• - Experience providing technical leadership and mentoring engineering teams.
• - Strong analytical, problem-solving, communication, and stakeholder management skills.