- Mountain View, California, United States
- Mid
- 0–2 years
We're building the runtime infrastructure that powers Moveworks' AI agents — the systems that orchestrate, execute, and deliver agent responses to millions of enterprise users in real time. This is not an ML role. This is a distributed systems engineering role at the heart of the agentic AI wave.
Responsibilities
- Agent orchestration engine — A state machine that manages long-running agent sessions, coordinating planning, execution, and user interaction across multiple LLM calls and tool invocations
- Distributed session management — Lease-based ownership using DynamoDB conditional writes, heartbeat protocols, and crash recovery via checkpointing
- Event-driven message pipeline — SQS FIFO queues for ordered delivery, Kafka consumers for event processing, and real-time streaming via gRPC and Socket.IO
- Structured concurrency — Python asyncio TaskGroups running multiple concurrent tasks per session (message polling, lease heartbeats, output publishing, orchestrator execution) with fail-fast semantics and graceful cancellation
- Observability infrastructure — OpenTelemetry instrumentation, distributed trace context propagation across async boundaries, custom span lifecycle management for sessions that span minutes