Lead Agentic AI Engineer

EPAM Systems; Argentina; Remote; ARS 1,200,000 - 1,800,000; Full time

Benefits offered by this job

Healthcare benefits

Paid time off

Sick leave

Upskilling and certifications

LinkedIn Learning access

Job summary

EPAM Systems, Inc. seeks a Lead Agentic AI Engineer to design, build, and operate scalable autonomous agent systems for production AI deployments in Argentina.

You will architect end-to-end solutions across runtime, memory, identity, tools, and observability, and lead adoption of AWS Bedrock AgentCore and Strands SDKs to power agent harnesses and releases.

Qualifications

• 5+ years building production software and 2+ years deploying LLM-based agents to production.
• Expert Python skills with hands-on agentic frameworks and SDKs.
• Experience with AWS Bedrock AgentCore components and related tooling.

Responsibilities

• Architect end-to-end autonomous agent systems for production deployments.
• Lead adoption of Bedrock AgentCore and agent SDKs across teams.
• Design memory, identity, tools, and observability for reliable agents.
• Develop MCP servers and integrate agent tools and scanners.

Skills

Python

LLM agents

Agent frameworks

AWS Bedrock AgentCore

Observability

Memory management

Prompt engineering

Tool integration

Tools

Strands

LangGraph

Claude Agent SDK

OpenAI Agents SDK

CrewAI

Job description

We are seeking a Lead Agentic AI Engineer to design, build, and operate scalable autonomous agent systems for production AI deployments. You will drive key decisions across runtime, memory, identity, tools, and observability while leading adoption of Amazon Bedrock AgentCore and related SDKs.ResponsibilitiesArchitect end-to-end systems to build, deploy, and run autonomous agents across runtime, memory, identity, tools, and observabilityLead adoption of AWS Bedrock AgentCore and the Strands Agents SDK to power agent harnesses and production releasesDesign long-term memory and context-management capabilities that support sustained multi-step engagementsBuild and maintain MCP servers and agent tool integrations such as recon tools, scanners, exploit primitives, and internal custom servicesOptimize agent reasoning for higher reliability, improved cost-efficiency, and faster executionDefine standards for evaluations, tracing, and guardrailsRequirementsProven track record with 5+ years building production software, including 2+ year deploying LLM-based agents to productionExpert Python skills and hands-on experience with agentic frameworks like Strands, LangGraph, Claude Agent SDK, OpenAI Agents SDK, or CrewAIHands-on knowledge of AWS Bedrock AgentCore components—Runtime, Memory, Identity, Gateway, and Observability—or the ability to ramp up quicklySolid background in MCP, tool use, prompt/context engineering, memory architectures, and agent evaluation methodsDeep understanding of production-grade design, including observability, guardrails, retry logic, cost management, and security boundariesEnglish proficiency at B2 (Upper-Intermediate) level or higherNice to haveExperience with application security, web pentesting, or red-teamingFamiliarity with sandboxed code execution, browser agents, or autonomous tool orchestrationWe offerInternational projects with top brandsWork with global teams of highly skilled, diverse peersHealthcare benefitsEmployee financial programsPaid time off and sick leaveUpskilling, reskilling and certification coursesUnlimited access to the LinkedIn Learning library and 22,000+ coursesGlobal career opportunitiesVolunteer and community involvement opportunitiesEPAM Employee GroupsAward-winning culture recognized by Glassdoor, Newsweek and LinkedIn