Chief Agentic AI Engineer

EPAM Systems; Argentina; Remote; ARS 3,000,000 - 6,000,000; Full time

Job summary

EPAM Systems, Inc. seeks a Chief Agentic AI Engineer to architect production-grade autonomous agents across runtime, memory, identity, tools and observability. You will guide adoption of AWS Bedrock AgentCore and Strands, shaping long-term memory and context management.

You will build MCP-based servers, integrate agent tools, and optimize reasoning for reliability, cost, and speed, while establishing guardrails and evaluation standards for complex multi-step engagements.

Qualifications

• 7+ years of production software experience.
• 2+ years deploying LLM-based agents in production.
• Strong Python and cloud/native stack knowledge.

Responsibilities

• Architect end-to-end autonomous agent platforms across runtime, memory, identity, tools, and observability.
• Lead adoption of AWS Bedrock AgentCore and Strands SDK for production launches.
• Design durable memory and context management for multi-step engagements.
• Build MCP servers and tool integrations used by agents.
• Optimize agent reasoning for reliability, cost, and speed.
• Define evaluations, tracing, and guardrails standards.

Skills

Python

LLM Agents deployment

Agent frameworks

System architecture

Observability

Security & guardrails

English (B2+)

Tools

AWS Bedrock AgentCore

MCP

Tool integrations

Sandboxed execution knowledge

Job description

We are 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.ResponsibilitiesArchitect end-to-end platforms for building, deploying, and operating 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 launchesDesign durable long-term memory and context-management capabilities that support multi-step engagementsBuild and sustain MCP servers and tool integrations agents depend on, including recon tools, scanners, exploit primitives, and internal custom servicesOptimize agent reasoning to improve reliability, cost-efficiency, and speedDefine standards for evaluations, tracing, and guardrailsRequirementsProven production software experience (7+ years), including 2+ year deploying LLM-based agents into productionAdvanced Python skills with hands-on use of agentic frameworks such as Strands, LangGraph, Claude Agent SDK, OpenAI Agents SDK, or CrewAIWorking knowledge of AWS Bedrock AgentCore components (Runtime, Memory, Identity, Gateway, Observability) or the ability to ramp up quicklyStrong understanding of MCP, tool use, prompt/context engineering, memory architectures, and agent evaluation approachesDemonstrated ability to design production-ready systems with 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