Software Engineer, Agentic Systems - Moveworks

ServiceNow•Mountain View, CA

About The Position

Moveworks is seeking a Software Engineer, Agentic Systems to build and own the runtime infrastructure powering its AI agents. This is a distributed systems engineering role, not an ML role. The infrastructure orchestrates, executes, and delivers agent responses to enterprise users in real time, supporting agents that plan and execute multi-step workflows, call tools, pause for human input, and resume while maintaining correctness, observability, and low latency. The work includes developing an agent orchestration engine for long-running sessions; distributed session management with lease-based ownership and crash recovery; event-driven messaging and real-time streaming; concurrent asynchronous execution; observability across asynchronous operations and long-running sessions; and caching and state layers. The role requires production backend or infrastructure experience, strength in Python or Go, and comfort addressing novel problems without established textbook solutions.

Requirements

  • Deep experience in at least three of the following areas: distributed systems; concurrent or asynchronous programming; event-driven architectures; database systems for infrastructure; observability; or gRPC/protobuf.
  • 0–2+ years building production backend or infrastructure systems.
  • Strong proficiency in Python or Go; ideally both.
  • Experience designing and operating systems that handle real traffic at scale.
  • Comfort with ambiguity and novel problems without textbook solutions.
  • Relevant distributed systems experience may include consistency models, idempotency, exactly-once delivery, and distributed locking or leasing.
  • Relevant concurrency experience may include Python asyncio, Go goroutines, structured concurrency, and cancellation handling.
  • Relevant event-driven architecture experience may include SQS, Kafka, pub/sub, backpressure, and delivery guarantees.
  • Relevant database experience may include DynamoDB conditional writes and transactions, and Redis connection pooling or pub/sub.
  • Relevant observability experience may include OpenTelemetry, distributed tracing, span context propagation, and Prometheus metrics.
  • Relevant gRPC/protobuf experience may include streaming RPCs, service interface design, and error-handling patterns.

Responsibilities

  • Build and own the runtime infrastructure that orchestrates, executes, and delivers AI agent responses.
  • Develop an orchestration state machine for long-running agent sessions across planning, execution, LLM calls, tool invocations, and user interactions.
  • Implement distributed session management using lease-based ownership, heartbeats, and checkpoint-based crash recovery.
  • Build event-driven message pipelines using ordered queues, event processing, and real-time streaming.
  • Implement concurrent asynchronous tasks for message polling, lease heartbeats, output publishing, and orchestrator execution, including cancellation and fail-fast behavior.
  • Build observability infrastructure, including instrumentation and distributed trace context propagation across asynchronous boundaries and long-running sessions.
  • Develop caching and state layers using Redis and DynamoDB, including scoped storage, batch read optimization, and hot-reload configuration.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service