GenAI Architect

Epam Systems; Gurugram District; Hybrid; INR 5,000,000 - 7,000,000; Full time

Job summary

Epam Systems is seeking a GenAI Architect to define and lead enterprise Generative AI architectures. You will shape strategy for agentic AI, multi-agent systems, and scalable LLM-powered apps, collaborating with security, data, and product teams.

The role requires hands-on Python, strong architecture skills, and experience with cloud AI services across AWS, Azure, or GCP.

Qualifications

• Must have experience designing GenAI/LLM architectures.
• Proven track record in enterprise-scale AI solutions.
• Strong security, governance, observability, and reliability focus.

Responsibilities

• Define the technical vision and strategy for enterprise Generative AI initiatives.
• Architect scalable LLM-powered applications and AI agent ecosystems.
• Design agent orchestration architectures and integration with enterprise APIs and tools.
• Define patterns for RAG, agentic RAG, memory, planning, and multi-agent collaboration.
• Evaluate LLMs, agent frameworks, vector databases, and cloud AI platforms.
• Provide architectural guidance to development teams and stakeholders.
• Create reusable GenAI reference architectures and engineering standards.

Skills

Python

LLMs

GenAI

Architectures

Distributed systems

API design

Cloud platforms

Leadership

Tools

LangGraph

LangChain

Google ADK

CrewAI

AutoGen

Microsoft Copilot extensibility

Pinecone

Weaviate

Qdrant

ChromaDB

FastAPI

Flask

REST/gRPC

Job description

Python GenAI Architect:

Experience: 1216 Years

Role: GenAI Architect / AI Solution Architect

Role Overview:

We are seeking an experienced Generative AI Architect to define and lead the architecture of enterprise-scale Generative AI, Agentic AI, and multi-agent solutions. The ideal candidate will combine deep software architecture expertise with strong hands-on experience in Python, LLMs, RAG, AI agents, cloud AI platforms, and enterprise integration.

The Architect will be responsible for translating business and technology requirements into secure, scalable, reliable, observable, and cost-effective AI architectures.

Key Responsibilities:

• Define the technical vision, architecture, and solution strategy for enterprise Generative AI and Agentic AI initiatives.
• Architect scalable LLM-powered applications, AI agents, multi-agent systems, and enterprise AI platforms.
• Design agent orchestration architectures using LangGraph, LangChain, Google ADK, CrewAI, AutoGen, Microsoft Copilot extensibility, or equivalent technologies.
• Define architecture patterns for RAG, Agentic RAG, tool/function calling, planning, reasoning, reflection, memory, human-in-the-loop, and multi-agent collaboration.
• Evaluate and select appropriate LLMs, agent frameworks, vector databases, AI platforms, and supporting technologies based on business and technical requirements.
• Architect enterprise integrations between LLMs/agents and APIs, microservices, enterprise applications, databases, knowledge repositories, and external tools.
• Define scalable backend and API architectures using Python, FastAPI/Flask, REST/gRPC, asynchronous programming, containers, and microservices.
• Design enterprise-grade RAG and knowledge architectures, including document ingestion, chunking, embeddings, retrieval, reranking, vector search, metadata, and knowledge management.
• Establish architecture principles for security, privacy, governance, responsible AI, access control, data protection, and auditability.
• Define strategies for LLM evaluation, observability, monitoring, quality, latency, reliability, and cost optimization.
• Establish standards for prompt engineering, structured outputs, guardrails, agent reliability, evaluation, and production readiness.
• Assess and define appropriate cloud AI architectures using Azure OpenAI, AWS Bedrock, Google Vertex AI, or equivalent platforms.
• Provide technical direction to Lead Engineers and development teams through architecture reviews, design reviews, POCs, and technical guidance.
• Define reusable GenAI reference architectures, design patterns, frameworks, accelerators, and engineering standards.
• Drive technology evaluations, PoCs, and innovation initiatives across emerging GenAI and Agentic AI technologies.
• Collaborate with enterprise architects, product leaders, engineering teams, data teams, security teams, and business stakeholders.
• Create and maintain architecture documentation, technical standards, ADRs, solution blueprints, and implementation guidelines

Required Qualifications

• Must Have
• 1216 years of overall software engineering/architecture experience.
• 4+ years of hands-on experience designing and implementing Generative AI/LLM solutions.
• Strong expertise in Python, software architecture, system design, distributed systems, APIs, and cloud-native applications.
• Proven experience architecting enterprise-scale GenAI, Agentic AI, or AI platform solutions.
• Deep hands-on experience with multiple Agentic AI frameworks such as LangGraph, LangChain, Google ADK, CrewAI, AutoGen, or Microsoft Copilot extensibility.
• Strong expertise in LLM architecture, RAG, Agentic RAG, multi-agent systems, tool calling, planning, memory, ReAct, guardrails, and human-in-the-loop patterns.
• Strong knowledge of OpenAI GPT, Anthropic Claude, Google Gemini, and open-source LLM ecosystems.
• Strong experience designing RAG platforms using Pinecone, Weaviate, Qdrant, ChromaDB, or equivalent technologies.
• Experience architecting REST/gRPC APIs, microservices, asynchronous systems, event-driven architectures, and distributed applications.
• Strong knowledge of AI security, governance, observability, evaluation, scalability, reliability, and cost optimization.
• Experience with enterprise cloud platforms such as AWS, Azure, or GCP, including AI services such as AWS Bedrock, Azure OpenAI, or Google Vertex AI.
• Strong technical leadership, stakeholder management, communication, and architecture governance skills.