Chief Agentic AI Engineer

EPAM Systems Inc; United States; Remote; USD 180,000 - 260,000; Full time

Job summary

EPAM Systems Inc. seeks a Chief Agentic AI Engineer to define architectures for autonomous agents, covering runtime, memory, identity, tools, and observability.

You will drive adoption of AWS Bedrock AgentCore and the Strands Agents SDK across harnesses and production deployments, and architect memory/context systems that endure over multi-step engagements.

Must have 7+ years in production software and 2+ years shipping LLM-based agents, with strong Python and security-focused design skills.

Qualifications

• 7+ years building production software.
• 2+ years shipping LLM-based agents to production.
• Proficient in Python with agent frameworks.
• Knowledge of AWS Bedrock AgentCore primitives.
• Strong observability, guardrails, retries, cost control.

Responsibilities

• Define architecture for autonomous agents (runtime, memory, identity, tools, observability).
• Champion adoption of AWS Bedrock AgentCore and Strands SDK in production.
• Architect long-term memory and context-management across multi-step engagements.
• Create and maintain MCP servers and tool integrations agents call.
• Optimize reliability, cost, latency; establish evals, tracing, and guardrails.

Skills

Python

LLM agents

Agent frameworks

AWS Bedrock

Observability

Security boundaries

Tools

Strands

LangGraph

Claude Agent SDK

OpenAI Agents SDK

CrewAI

Job description

Chief Agentic AI Engineer

Responsibilities

• Define architecture for building, deploying, and operating autonomous agents, covering runtime, memory, identity, tools, and observability
• Champion adoption of AWS Bedrock AgentCore and the Strands Agents SDK across agent harnesses and production deployments
• Architect long-term memory and context-management systems that remain effective across multi-step engagements
• Create and maintain MCP servers and tool integrations agents call, including recon, scanners, exploit primitives, and custom internal services
• Optimize reliability, cost, and latency of agent reasoning, and establish standards for evals, tracing, and guardrails

Requirements

• Proven experience building production software, including 7+ years overall and 2+ years shipping LLM-based agents to production
• Expert proficiency in Python with hands‑on use of an agentic framework such as Strands, LangGraph, Claude Agent SDK, OpenAI Agents SDK, or CrewAI
• Working knowledge of AWS Bedrock AgentCore primitives, including Runtime, Memory, Identity, Gateway, and Observability, or a demonstrated ability to ramp up quickly
• Deep understanding of MCP, tool use, prompt/context engineering, memory architectures, and agent evaluation
• Strong production design skills spanning observability, guardrails, retries, cost control, and security boundaries
• English proficiency at B2 (Upper-Intermediate) level or higher
• Nice to have Experience in application security, web pentesting, or red‑teaming
• Exposure to sandboxed code execution, browser agents, or autonomous tool orchestration