Senior Python & LangGraph Engineer — AI Agent Orchestration

EPAM Systems; United States; Remote; USD 120,000 - 150,000; Full time

Job summary

EPAM Systems is seeking a Senior Python / LangGraph Engineer to join the team building an Enterprise Agent Development Platform on AWS. You will design Python LangGraph nodes and graphs for orchestration, implement checkpointing with SQLite/Redis/Postgres, and build HITL workflows to support controlled decision points.

You will also implement retry/timeout/fallback patterns, apply OpenTelemetry tracing for observability, and collaborate to standardize LangGraph practices across the platform.

Qualifications

• 5+ years of Python development.
• Expertise in LangGraph or LangChain agent orchestration.
• Proficiency in async Python (asyncio).
• Experience with checkpointing using SQLite, Redis, and Postgres checkpointers.
• Background in HITL workflow implementation.
• Knowledge of retry, timeout, and fallback patterns in LangGraph.
• Understanding of OpenTelemetry tracing across orchestration steps.

Responsibilities

• Design and implement Python-based LangGraph nodes, edges, and graphs for agent orchestration delivery
• Build checkpointing mechanisms using SQLite, Redis, and Postgres checkpointers within LangGraph
• Develop human-in-the-loop (HITL) workflows to support controlled agent decision points
• Implement retry, timeout, and fallback patterns to ensure reliable orchestration behavior
• Integrate OpenTelemetry tracing across orchestration steps for full pipeline observability
• Collaborate with the Development framework team to standardize LangGraph orchestration practices
• Contribute to the reliability and scalability of agent workflows deployed on AWS AgentCore Runtime
• Support the evolution of the platform's single-file developer experience for agent builders

Skills

Python development

LangGraph/LangChain orchestration

asyncio

checkpointing (SQLite/Redis/Postgres)

HITL workflows

retry/timeout/fallback patterns

OpenTelemetry tracing

AWS Bedrock familiarity

multi-agent workflow testing

LangSmith tracing visualization

Job description

EPAM Systems is seeking a Senior Python / LangGraph Engineer to join the team building an Enterprise Agent Development Platform on AWS. You will design Python LangGraph nodes and graphs for orchestration, implement checkpointing with SQLite/Redis/Postgres, and build HITL workflows to support controlled decision points.

You will also implement retry/timeout/fallback patterns, apply OpenTelemetry tracing for observability, and collaborate to standardize LangGraph practices across the platform.