Senior AI Engineer with Amazon Bedrock AgentCore

We are looking for a Senior AI Engineer to join our team and own the Agent Orchestration Framework, covering multi-agent orchestration patterns, checkpointing/state management, and human-in-the-loop workflow design as part of our Enterprise Agent Development Platform — a production-grade, cloud-native ecosystem that enables engineering teams to define, orchestrate, deploy, and observe AI agents at scale. The platform standardizes agent development across the organization using LangGraph and Strands Agents on AWS AgentCore Runtime, providing a single-file developer experience where the platform handles runtime, tooling, observability, and deployment automatically.

Responsibilities

• Own the design and evolution of the Agent Orchestration Framework across the platform
• Design and implement multi-agent orchestration patterns such as supervisor/worker and fan-out/fan-in
• Build and maintain checkpointing and state management mechanisms within LangGraph workflows
• Architect human-in-the-loop (HITL) workflows to support enterprise approval processes
• Enable A2A agent delegation through the Agent Gateway
• Develop and maintain agent runtimes on AWS Bedrock AgentCore Runtime
• Collaborate with engineering teams to standardize agent development practices across the organization
• Ensure observability, reliability, and scalability of deployed agents in production environments

Requirements

• 5+ years of experience in Python engineering
• Hands-on experience with LangGraph and LangChain for multi-step agent workflows
• Experience with AWS Bedrock AgentCore Runtime
• Experience with workflow orchestration tools such as Temporal or Airflow, or equivalent platforms
• Knowledge of stateful distributed system patterns, including checkpointing and idempotency
• Understanding of multi-agent orchestration patterns, including supervisor/worker and fan-out/fan-in designs
• Familiarity with human-in-the-loop (HITL) workflow design

Nice to have

• Experience evaluating AWS AgentCore Runtime maturity
• Familiarity with AWS Bedrock Memory API
• Experience integrating enterprise HITL approval workflows

We offer

CONTINUOUS UPSKILLING, LEARNING & DEVELOPMENT

• Diversity of tasks and projects
• Assessment center for objective review of competency level
• Personal development plan
• Mentoring programs and leadership development
• Certification and professional development support 
• Access to learning platforms including more than 2,500 internal courses
• English courses taught by certified teachers

CORPORATE BENEFITS

• Extra leave days
• Referral bonuses

COMPENSATION PACKAGE

• Competitive compensation paid in USD
• Regular salary and performance reviews

MEDICAL & HEALTHCARE

• Private health insurance
• Well-being events

WORKING ENVIRONMENT

• Recreation areas and kitchens
• Tea, coffee and snacks
• Sports equipment and game consoles
• IT Equipment
• Microsoft’s Software Assurance Home Use Program (HUP)

Please note that our Talent Attraction Team reviews applications and CVs submitted in English.

EPAM is global leader in AI transformation engineering and integrated consulting, serving Forbes Global 2000 companies and ambitious startups. With over thirty years of expertise in custom software, product and platform engineering, we empower our clients to become AI-Native enterprises, driving measurable value from innovation and digital investments.

Remote in Türkiye