Principal Autonomous AI Engineer — AgentCore Architect

EPAM Systems; México; On-site; MXN 1,000,000 - 2,000,000; Full time

Benefits offered by this job

Healthcare benefits

Paid time off

Upskilling programs

Global career opportunities

Job summary

EPAM Systems is seeking a Chief Agentic AI Engineer to build production-grade autonomous agent systems and drive architecture across runtime, memory, identity, tools, and observability.

You will lead critical technical decisions, guide adoption of AWS Bedrock AgentCore and Strands, and set standards for MCP-based tooling, evaluations, and guardrails. The role collaborates with multi-national teams and requires hands-on cloud experience and leadership.

Qualifications

• 7+ years production software experience, including 2+ years deploying LLM-based agents.
• Strong Python skills and hands-on use of agentic frameworks like Strands, LangGraph, Claude Agent SDK, OpenAI Agents SDK, or CrewAI.
• Experience with AWS Bedrock AgentCore components.

Responsibilities

• Architect end-to-end platforms for autonomous agents across runtime, memory, identity, tools, and observability.
• Lead adoption of AWS Bedrock AgentCore and the Strands Agents SDK to power agent harnesses and production launches.
• Design durable memory and context-management capabilities for multi-step engagements.
• Build and sustain MCP servers and tool integrations agents depend on, including recon tools and internal services.
• Optimize agent reasoning to improve reliability, cost-efficiency, and speed.
• Define standards for evaluations, tracing, and guardrails.

Skills

Python

LLM deployment

Agent frameworks

AWS Bedrock

MCP architectures

Prompt engineering

English B2

Tools

LangGraph

Claude Agent SDK

OpenAI Agents SDK

CrewAI

Strands

Job description

EPAM Systems is seeking a Chief Agentic AI Engineer to build production-grade autonomous agent systems and drive architecture across runtime, memory, identity, tools, and observability.

You will lead critical technical decisions, guide adoption of AWS Bedrock AgentCore and Strands, and set standards for MCP-based tooling, evaluations, and guardrails. The role collaborates with multi-national teams and requires hands-on cloud experience and leadership.