Senior Agentic AI Engineer

EPAM Systems Inc; United States; Remote; USD 150,000 - 230,000; Full time

Job summary

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

You will lead architecture for runtime, memory, identity, tools, and observability; ship LLM-based agents and collaborate with security and performance teams to maintain guardrails and cost efficiency.

Qualifications

• 3+ years of experience building production software, including 1+ years shipping LLM-based agents to production.
• Proficiency in Python and hands-on experience with an agentic framework such as Strands, LangGraph, Claude Agent SDK, OpenAI Agents SDK, or CrewAI.

Responsibilities

• Design the architecture for building, deploying, and operating autonomous agents, including runtime, memory, identity, tools, and observability.
• Lead the use of AWS Bedrock AgentCore and the Strands Agents SDK across agent harnesses and production deployments.
• Design long‑term memory and context-management systems that hold up across multi‑step engagements.
• Build and curate MCP servers and tool integrations the agents call out to, such as recon, scanners, exploit primitives, and custom internal services.
• Drive reliability, cost, and latency of agent reasoning, and set the bar for evals, tracing, and guardrails.

Skills

Python

Agent Frameworks

AWS Bedrock

Observability

Tools

Strands SDK

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.

Responsibilities

• Design the architecture for building, deploying, and operating autonomous agents, including runtime, memory, identity, tools, and observability
• Lead the use of AWS Bedrock AgentCore and the Strands Agents SDK across agent harnesses and production deployments
• Design long‑term memory and context‑management systems that hold up across multi‑step engagements
• Build and curate MCP servers and tool integrations the agents call out to, such as recon, scanners, exploit primitives, and custom internal services
• Drive reliability, cost, and latency of agent reasoning, and set the bar for evals, tracing, and guardrails

Requirements

• 3+ years of experience building production software, including 1+ years shipping LLM‑based agents to production
• Proficiency in Python and hands‑on experience with an agentic framework such as Strands, LangGraph, Claude Agent SDK, OpenAI Agents SDK, or CrewAI
• Familiarity with AWS Bedrock AgentCore primitives, including Runtime, Memory, Identity, Gateway, and Observability, or proven ability to ramp up fast
• Understanding of MCP, tool use, prompt/context engineering, memory architectures, and agent evaluation
• Skills in designing for production, including observability, guardrails, retries, cost control, and security boundaries
• English proficiency at B2 level or higher

Nice to have

• Background in application security, web pentesting, or red‑teaming
• Experience with sandboxed code execution, browser agents, or autonomous tool orchestration