Staff Distributed Systems Engineer, Agentic AI (Remote)

Moveworks; Mountain View, Northern (CA, KY); Hybrid; USD 180,000 - 260,000; Full time

Job summary

Moveworks is seeking a Staff Software Engineer to build and own the runtime infrastructure powering its Agentic AI agents. You will develop distributed systems that orchestrate, execute, and deliver responses to millions of enterprise users in real time.

This is a core backend engineering role, not an ML role. You will design and operate systems handling real traffic at scale, with a strong emphasis on correctness, observability, and low latency.

Qualifications

• 7+ years building production backend/infrastructure systems.
• Strong in Python or Go (ideally both).
• Experience designing and operating systems that handle real traffic at scale.
• Comfort with ambiguity — these are novel problems without textbook solutions.

Responsibilities

• Agent orchestration engine: a state machine coordinating planning, execution and user interaction across LLM calls and tool invocations.
• Distributed session management with DynamoDB-based ownership and heartbeat protocols.
• Event-driven message pipeline using SQS FIFO, Kafka, and real-time streaming with gRPC/Socket.IO.
• Structured concurrency with Python asyncio TaskGroups for multiple concurrent tasks per session.
• Observability infrastructure with OpenTelemetry and distributed tracing across async boundaries.
• Caching/state layers using Redis and DynamoDB with per-org/per-bot scoping.

Skills

Distributed systems

Async programming

System design

Ambiguity tolerance

Tools

DynamoDB

Redis

OpenTelemetry

Kafka

gRPC

Socket.IO

Job description

Moveworks is seeking a Staff Software Engineer to build and own the runtime infrastructure powering its Agentic AI agents. You will develop distributed systems that orchestrate, execute, and deliver responses to millions of enterprise users in real time.

This is a core backend engineering role, not an ML role. You will design and operate systems handling real traffic at scale, with a strong emphasis on correctness, observability, and low latency.