Principal Autonomous Agent Engineer

EPAM Systems; Chile; In loco; CLP 9.000.000 - 13.000.000; Tempo pieno

Vantaggi offerti da questo lavoro

Healthcare benefits

Paid time off and sick leave

Upskilling, reskilling and certificate

Global career opportunities

Volunteer and community involvement

Descrizione del lavoro

EPAM Systems seeks a Chief Agentic AI Engineer to architect production-grade autonomous agent platforms and drive standards for memory, identity, tools, and observability. You will lead critical technical decisions and guide adoption of AWS Bedrock AgentCore and Strands across runtime environments.

You will design durable memory mechanisms, MCP server ecosystems, and tool integrations to support multi-step engagements, optimizing cost, speed, and reliability while defining robust guardrails and

Competenze

• Proven production software experience (7+ years).
• 2+ years deploying LLM-based agents into production.

Mansioni

• Architect end-to-end platforms for building, deploying, and operating 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 long-term memory and context-management capabilities that support multi-step engagements.
• Build and sustain MCP servers and tool integrations agents depend on, including recon tools, scanners, exploit primitives, and internal custom services.
• Optimize agent reasoning to improve reliability, cost-efficiency, and speed.
• Define standards for evaluations, tracing, and guardrails.

Conoscenze

Python

Agentic frameworks

System design

Observability

Cloud AWS

Strumenti

Bedrock AgentCore

Strands SDK

LangGraph

Claude Agent SDK

OpenAI Agents SDK

Descrizione del lavoro

EPAM Systems seeks a Chief Agentic AI Engineer to architect production-grade autonomous agent platforms and drive standards for memory, identity, tools, and observability. You will lead critical technical decisions and guide adoption of AWS Bedrock AgentCore and Strands across runtime environments.

You will design durable memory mechanisms, MCP server ecosystems, and tool integrations to support multi-step engagements, optimizing cost, speed, and reliability while defining robust guardrails and