It all started when engineer Fred Luddy wrote code that automated a tedious task for his coworker, Phyllis. She cried tears of joy. Backed by Greylock and Sequoia.
About the role
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. Found on 1752vc Careers, the job board for startup and VC roles.
What they're looking for
- Distributed systems: consistency models, idempotency, exactly-once delivery, distributed locking/leasing
- Concurrent/async programming: Python asyncio, Go goroutines, structured concurrency, cancellation handling
- Event-driven architectures: message queues (SQS, Kafka), pub/sub, backpressure, delivery guarantees
- Database systems for infrastructure: DynamoDB (conditional writes, transactions), Redis (connection pooling, pub/sub)
- Observability: OpenTelemetry, distributed tracing, span context propagation, Prometheus metrics
- GRPC/protobuf: streaming RPCs, service interface design, error handling patterns
More about this role
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.
Our AI agents can plan, execute multi-step workflows, call tools, wait on human input, and resume — all while maintaining correctness, observability, and low latency. The systems that make this possible are what you'll build and own.
- 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...
Browse similar: Startup jobs · San Francisco Bay Area