Principal Autonomous AI Engineer - Agentic Systems

EPAM Systems; Chile; On-site; CLP 12,000,000 - 18,000,000; Full time

Benefits offered by this job

Healthcare benefits

Global career opportunities

Paid time off and sick leave

Upskilling and certification courses

LinkedIn Learning access

Job summary

EPAM Systems seeks a seasoned Chief Agentic AI Engineer to design and deploy scalable autonomous agent systems across runtime, memory, identity, tools, and observability. You will drive production-grade deployments using AWS Bedrock AgentCore and agentic frameworks to ensure reliability and robust guardrails.

Responsibilities include architecting agent ecosystems, memory management, and tool integrations, while optimizing cost, latency, and observability.

Qualifications

• 7+ years of experience building production software.
• 2+ years shipping LLM-based agents to production.
• Expert proficiency in Python and agentic frameworks.
• Experience with AWS Bedrock AgentCore primitives.
• Deep understanding of MCP, tool use, memory architectures, and agent evaluation.
• English proficiency at B2 level or higher.

Responsibilities

• Define architecture for autonomous agents across runtime, memory, identity, tools, observability.
• Champion Strands, LangGraph, Claude Agent SDK, OpenAI Agents SDK or CrewAI in deployments.
• Architect long-term memory and context-management for multi-step engagements.
• Develop and maintain MCP servers and tool integrations accessed by agents.
• Optimize reliability, cost, and latency of agent reasoning.
• Establish standards for evals, tracing and guardrails.

Skills

Python

Agent frameworks

AWS Bedrock AgentCore

Memory architectures

Observability and guardrails

Prompt engineering

Production software design

English communication (B2)

Tools

Strands

LangGraph

Claude Agent SDK

OpenAI Agents SDK

CrewAI

AWS Bedrock AgentCore primitives

Job description

EPAM Systems seeks a seasoned Chief Agentic AI Engineer to design and deploy scalable autonomous agent systems across runtime, memory, identity, tools, and observability. You will drive production-grade deployments using AWS Bedrock AgentCore and agentic frameworks to ensure reliability and robust guardrails.

Responsibilities include architecting agent ecosystems, memory management, and tool integrations, while optimizing cost, latency, and observability.