Lead Agentic AI Engineer for Production & Guardrails

EPAM Systems Inc; United States; Remote; USD 170,000 - 240,000; Full time

Job summary

EPAM Systems Inc. seeks a Lead Agentic AI Engineer to own scalable autonomous agent systems and production architecture, reliability, and operational excellence.

You will shape production-grade agentic workflows using AWS Bedrock AgentCore and proven agentic frameworks, improving evals, tracing, guardrails, and cost controls. You will define architecture for running agents, champion Strands and LangGraph ecosystems, build durable memory and context-management, and ensure secure, observable

Qualifications

• Proven track record with 5+ years of production software experience.
• 2+ years shipping LLM-based agents to production.

Responsibilities

• Define the architecture to build, deploy, and operate autonomous agents, covering runtime, memory, identity, tools, and observability.
• Champion the adoption of AWS Bedrock AgentCore and the Strands Agents SDK across agent harnesses and production deployments.
• Architect durable long-term memory and context-management systems across multi-step engagements.
• Create and maintain MCP servers and tool integrations that agents invoke (recon, scanners, exploit primitives, internal services).
• Optimize agent reasoning reliability, cost, latency, and set standards for evals, tracing, and guardrails.

Skills

Python

LLM-based agents

Agent frameworks

AWS Bedrock AgentCore

Observability

Security boundaries

English communication

Tools

Strands

LangGraph

Claude Agent SDK

OpenAI Agents SDK

CrewAI

AWS Bedrock AgentCore

Job description

EPAM Systems Inc. seeks a Lead Agentic AI Engineer to own scalable autonomous agent systems and production architecture, reliability, and operational excellence.

You will shape production-grade agentic workflows using AWS Bedrock AgentCore and proven agentic frameworks, improving evals, tracing, guardrails, and cost controls. You will define architecture for running agents, champion Strands and LangGraph ecosystems, build durable memory and context-management, and ensure secure, observable