Lead Agentic AI Engineer: Build Scalable Autonomous Agents

EPAM Systems, Inc.; United States; Remote; USD 180,000 - 260,000; Full time

Benefits offered by this job

Healthcare benefits

Paid time off

Upskilling and certification courses

LinkedIn Learning access

Global career opportunities

Job summary

EPAM Systems, Inc. is seeking a Lead Agentic AI Engineer to own scalable autonomous agent systems and production architecture, reliability, and operations.

You will craft production-grade agent workflows using AWS Bedrock AgentCore and leading agent frameworks, improving evals, tracing, guardrails, and cost controls while ensuring security and scalability across multi-step engagements. You will shape runtime, memory, identity, tools, and observability for agents, drive tool integrations, and

Qualifications

• 5+ years building production software.
• 2+ years deploying LLM-based agents to production.
• Strong Python proficiency.
• Experience with agentic frameworks in production.
• Familiar with AWS Bedrock AgentCore primitives.
• English at least B2+ communication.

Responsibilities

• Define the architecture to build, deploy, and operate autonomous agents across runtime, memory, identity, tools and observability.
• Champion adoption of AWS Bedrock AgentCore and the Strands SDK in production deployments.
• Architect durable memory and context-management systems for multi-step engagements.
• Create and maintain MCP servers and tool integrations that agents invoke.
• Optimize agent reasoning reliability, cost, latency; set standards for evals, tracing, guardrails.

Skills

Python

LLM Agents

Agent Frameworks

AWS Bedrock

Observability

Security

Prompt Engineering

Memory Architecture

Cost Control

English (B2+)

Tools

Strands

LangGraph

Claude Agent SDK

OpenAI Agents SDK

CrewAI

Job description

EPAM Systems, Inc. is seeking a Lead Agentic AI Engineer to own scalable autonomous agent systems and production architecture, reliability, and operations.

You will craft production-grade agent workflows using AWS Bedrock AgentCore and leading agent frameworks, improving evals, tracing, guardrails, and cost controls while ensuring security and scalability across multi-step engagements. You will shape runtime, memory, identity, tools, and observability for agents, drive tool integrations, and