Senior Distributed Systems Engineer — AI Agent Orchestration

Servicenow; Mountain View (CA); Híbrido; USD 180.000 - 240.000; Jornada completa

Descripción de la vacante

ServiceNow is seeking a distributed systems engineer to power Moveworks' AI agents at scale. You will build the runtime infrastructure that orchestrates, executes, and delivers responses to enterprise users in real time, with focus on correctness, observability, and low latency.

You will own the agent orchestration engine, session management, event-driven pipelines, and state layers, working with Python or Go, SQS/Kafka, DynamoDB/Redis, and OpenTelemetry to maintain reliability under heavy load.

Formación

• 10+ years building production backend/infrastructure systems.
• Strong in Python or Go (ideally both).
• Experience designing and operating systems that handle real traffic at scale.

Responsabilidades

• Agent orchestration engine — manage long-running sessions across multiple LLM calls and tools.
• Distributed session management with lease-based ownership and crash recovery.
• Event-driven message pipeline using SQS/Kafka and real-time streaming via gRPC.
• Structured concurrency with asynchronous tasks and graceful cancellation.
• Observability infrastructure with OpenTelemetry and distributed tracing.
• Caching and state layers using Redis and DynamoDB with per-org/per-bot scope.

Conocimientos

Distributed systems

Async programming

Event-driven architecture

Observability

gRPC

Python or Go

Educación

Bachelor's degree in CS/SE

Herramientas

SQS

Kafka

DynamoDB

Redis

OpenTelemetry

Descripción del empleo

ServiceNow is seeking a distributed systems engineer to power Moveworks' AI agents at scale. You will build the runtime infrastructure that orchestrates, executes, and delivers responses to enterprise users in real time, with focus on correctness, observability, and low latency.

You will own the agent orchestration engine, session management, event-driven pipelines, and state layers, working with Python or Go, SQS/Kafka, DynamoDB/Redis, and OpenTelemetry to maintain reliability under heavy load.