Head of Autonomous Agent Engineering

EPAM Systems; Argentina; Sur place; ARS 3 000 000 - 4 200 000; Plein temps

Avantages offerts par ce poste

Healthcare benefits

Learning programs (upskilling)

Global teams and career opportunities

Paid time off

Résumé du poste

EPAM Systems seeks a Chief Agentic AI Engineer to design, deploy, and operate autonomous agent systems at scale with production-grade reliability. You will shape end-to-end workflows across runtime, memory, identity, tools, and observability, raising standards for evaluation, tracing, and guardrails.

Responsibilities include architecting agent ecosystems, driving adoption of Bedrock AgentCore and Strands SDK, and building memory and context-management systems for multi-step engagements.

Qualifications

• 7+ years of software experience with 2+ years shipping production LLM agents.
• Proficiency in Python and agentic frameworks.
• Experience with agent memory, context, and observability.

Responsabilités

• Define architecture for autonomous agents across runtime, memory, identity, tools and observability.
• Champion adoption of AWS Bedrock AgentCore and Strands SDK in production.
• Architect long-term memory and context management for multi-step engagements.
• Create and maintain MCP servers and tool integrations for agent tooling and safety.
• Optimize reliability, cost and latency of agent reasoning; set evals and guardrails.

Connaissances

Python

Agent Frameworks

LLM Production

System Design

English B2+

Outils

Strands

LangGraph

Claude Agent SDK

OpenAI Agents SDK

CrewAI

AWS Bedrock AgentCore

Description du poste

EPAM Systems seeks a Chief Agentic AI Engineer to design, deploy, and operate autonomous agent systems at scale with production-grade reliability. You will shape end-to-end workflows across runtime, memory, identity, tools, and observability, raising standards for evaluation, tracing, and guardrails.

Responsibilities include architecting agent ecosystems, driving adoption of Bedrock AgentCore and Strands SDK, and building memory and context-management systems for multi-step engagements.