Senior Software Engineer, Agentic Platform - Moveworks
Remote • Mountain View, CALIFORNIA, United States • Full-time
Posted 1mo ago
Job Location
Mountain View, CALIFORNIA, United States
Tech Stack
Remote Work Policy
Fully remote
Employment Type
Full-time
Categories
AI Agent Engineer
About the job
We are seeking a Senior Software Engineer to join our team and build the runtime infrastructure that powers Moveworks' AI agents. These agents are responsible for orchestrating, executing, and delivering responses to millions of enterprise users in real time. This role focuses on distributed systems engineering at the forefront of agentic AI, enabling our AI agents to plan, execute multi-step workflows, call tools, and interact with users while maintaining correctness, observability, and low latency. You will build and own the core systems that make these advanced agent capabilities possible.
Responsibilities
- Develop and maintain the agent orchestration engine, a state machine managing long-running agent sessions across LLM calls and tool invocations.
- Implement distributed session management with lease-based ownership, heartbeat protocols, and crash recovery.
- Build an event-driven message pipeline using SQS FIFO queues and Kafka consumers for ordered delivery and real-time streaming.
- Utilize structured concurrency with Python asyncio TaskGroups for concurrent task management within sessions.
- Enhance observability infrastructure with OpenTelemetry instrumentation and distributed trace context propagation.
- Develop caching and state layers using Redis and DynamoDB for efficient data management and configuration.
Requirements
- 5+ years of experience building production backend/infrastructure systems.
- Strong proficiency in Python or Go, ideally both.
- Experience designing and operating systems that handle significant production traffic at scale.
- Deep experience in at least three of the following areas: distributed systems (consistency, idempotency, locking), concurrent/async programming (Python asyncio, Go), event-driven architectures (message queues, pub/sub), database systems for infrastructure (DynamoDB, Redis), observability (OpenTelemetry, tracing), or gRPC/protobuf.
- Comfort with ambiguity and solving novel problems.