Senior Agentic AI Engineer

EPAM Systems, Inc.; United States; Remote; USD 140,000 - 220,000; Full time

Benefits offered by this job

Healthcare benefits

Paid time off

Job summary

EPAM Systems, Inc. is seeking a Senior Agentic AI Engineer to design, build, and operate autonomous agent systems at scale, driving production-grade agentic workflows.

You will architect agent runtime, memory, identity, tools, and observability, and lead across deployments with AWS Bedrock AgentCore and the Strands SDK. Expect collaboration with global teams to deliver reliable, cost-efficient agent orchestration.

Qualifications

• 3+ years of experience building production software.
• 1+ years shipping LLM-based agents to production.
• Proficiency in Python.
• Hands-on experience with agentic frameworks (e.g., Strands, LangGraph, Claude Agent SDK, OpenAI Agents SDK, or CrewAI).
• Familiarity with AWS Bedrock AgentCore primitives (Runtime, Memory, Identity, Gateway, Observability).
• Understanding of MCP, tool use, memory architectures, and agent evaluation.
• Design for production: observability, guardrails, retries, cost control, and security.

Responsibilities

• Design the architecture for building and operating autonomous agents at scale.
• Lead use of AWS Bedrock AgentCore and Strands SDK across deployments.
• Develop long-term memory and context-management for multi-step engagements.
• Build MCP servers and tool integrations used by agents (recon, scanners, internal services).
• Improve reliability, latency, and cost, and establish guardrails and evals.

Skills

Python

LLM agents

Agent frameworks

Observability

Performance optimization

Tools

AWS Bedrock AgentCore

LangGraph

Claude Agent SDK

OpenAI Agents SDK

CrewAI

Job description

We are seeking a Senior Agentic AI Engineer to design, build, and operate autonomous agent systems at scale, driving the architecture and reliability of production-grade agentic workflows.ResponsibilitiesDesign the architecture for building, deploying, and operating autonomous agents, including runtime, memory, identity, tools, and observabilityLead the use of AWS Bedrock AgentCore and the Strands Agents SDK across agent harnesses and production deploymentsDesign long-term memory and context-management systems that hold up across multi-step engagementsBuild and curate MCP servers and tool integrations the agents call out to, such as recon, scanners, exploit primitives, and custom internal servicesDrive reliability, cost, and latency of agent reasoning, and set the bar for evals, tracing, and guardrailsRequirements3+ years of experience building production software, including 1+ years shipping LLM-based agents to productionProficiency in Python and hands-on experience with an agentic framework such as Strands, LangGraph, Claude Agent SDK, OpenAI Agents SDK, or CrewAIFamiliarity with AWS Bedrock AgentCore primitives, including Runtime, Memory, Identity, Gateway, and Observability, or proven ability to ramp up fastUnderstanding of MCP, tool use, prompt/context engineering, memory architectures, and agent evaluationSkills in designing for production, including observability, guardrails, retries, cost control, and security boundariesEnglish proficiency at B2 level or higherNice to haveBackground in application security, web pentesting, or red-teamingExperience 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