Chief Agentic AI Engineer

EPAM Systems, Inc.; Colombia; A distancia; COP 397.390.000 - 695.433.000; Jornada completa

Descripción de la vacante

EPAM Systems, Inc. seeks a Chief Agentic AI Engineer to architect and run autonomous agent systems at scale with production-grade reliability.

You will shape end-to-end agent workflows across runtime, memory, identity, tools, and observability while elevating evaluation, tracing, and guardrails. You will lead adoption of AWS Bedrock AgentCore and Strands SDK, design long-term memory architectures, and drive tool integrations.

Formación

• 7+ years of overall software experience.
• 2+ years shipping LLM-based agents to production.
• Proficient in Python and agentic frameworks.
• Strong knowledge of memory, tool-use, prompt/context engineering, and evaluation.
• Experience with observability, guardrails, retries, and security boundaries.

Responsabilidades

• Define architecture for autonomous agents across runtime, memory, identity, tools and observability.
• Champion adoption of AWS Bedrock AgentCore and Strands across deployments.
• Architect long-term memory and context management for multi-step engagements.
• Create MCP servers and tool integrations agents call, including recon, scanners, exploit primitives, and internal services.
• Optimize reliability, cost, latency of agent reasoning and establish evals, tracing, and guardrails.

Conocimientos

Python

LLM agents

Agent framework

Observability

Security boundaries

Memory architectures

English (B2)

Herramientas

Strands

LangGraph

Claude Agent SDK

OpenAI Agents SDK

CrewAI

AWS Bedrock AgentCore

Descripción del empleo

We are seeking a Chief Agentic AI Engineer to architect, deliver, and run autonomous agent systems at scale with production-grade reliability. You will shape end-to-end agentic workflows across runtime, memory, identity, tools, and observability while raising the bar for evaluation, tracing, and guardrails.ResponsibilitiesDefine architecture for building, deploying, and operating autonomous agents, covering runtime, memory, identity, tools, and observabilityChampion adoption of AWS Bedrock AgentCore and the Strands Agents SDK across agent harnesses and production deploymentsArchitect long-term memory and context-management systems that remain effective across multi-step engagementsCreate and maintain MCP servers and tool integrations agents call, including recon, scanners, exploit primitives, and custom internal servicesOptimize reliability, cost, and latency of agent reasoning, and establish standards for evals, tracing, and guardrailsRequirementsProven experience building production software, including 7+ years overall and 2+ years shipping LLM-based agents to productionExpert proficiency in Python with hands-on use of an agentic framework such as Strands, LangGraph, Claude Agent SDK, OpenAI Agents SDK, or CrewAIWorking knowledge of AWS Bedrock AgentCore primitives, including Runtime, Memory, Identity, Gateway, and Observability, or a demonstrated ability to ramp up quicklyDeep understanding of MCP, tool use, prompt/context engineering, memory architectures, and agent evaluationStrong production design skills spanning observability, guardrails, retries, cost control, and security boundariesEnglish proficiency at B2 (Upper-Intermediate) level or higherNice to haveExperience in application security, web pentesting, or red-teamingExposure to 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 LinkedInEPAM is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, age, sexual orientation, gender identity or expression, disability, protected veteran status, or any other characteristic protected by applicable law.