Building the verification layer that monitors AI agent behavior at scale.
Senior Backend/Infrastructure Engineer
We're a small, well-funded team in San Francisco tackling a problem that grows more urgent by the day: how do you trust autonomous agents when they're making thousands of decisions per second? Our platform observes, records, and validates agent actions across production systems — surfacing anomalies, policy violations, and silent failures before they compound into disasters. We need an engineer who thinks in distributed systems and gets genuinely excited about the intersection of event-driven architectures and AI safety. You'll design the data pipelines and infrastructure that ingest billions of agent events, make them queryable in real time, and keep the entire system resilient under wildly spiky workloads.
What they're looking for
- Deep experience with at least one major cloud provider (AWS, GCP, or Azure) and the ability to reason across multi-cloud tradeoffs
- Fluency with Kubernetes in production — you've debugged cluster-level issues at 3am and have opinions on what belongs in a pod versus what doesn't
- Track record building on event streaming platforms like Kafka or RabbitMQ, including partition strategies, backpressure handling, and exactly-once semantics
- Proficiency with infrastructure-as-code (Terraform) and a conviction that manual changes are technical debt
- Comfortable owning observability, alerting, and incident response for systems where a five-minute degradation has real customer consequences