AI Infrastructure Engineer

The Opportunity

‍

Every agent we ship is only as reliable as the infrastructure underneath it. As our AI Infrastructure Engineer, you'll own the systems that route, queue, and scale inference requests across our platform — the layer nobody sees until it breaks.

‍

You'll work at the intersection of distributed systems and ML serving, making calls about caching, autoscaling, and failover that directly affect latency for every customer running agents on our platform.

‍

What a Typical Engagement Looks Like

‍

Traffic spikes 4x during a customer's product launch, and your autoscaling policies are the reason nothing falls over. You're the one tuning the load balancers, watching GPU utilization in real time, and deciding whether to spin up new inference nodes or reroute to a warm pool.

‍

On a quieter week, you're profiling p99 latency across our model endpoints, shaving milliseconds off the request path, and writing the runbooks that let on-call engineers resolve incidents without waking you up.

‍

Your Responsibilities

‍

• Design and maintain scalable inference infrastructure for high-concurrency agent workloads
• Own autoscaling, load balancing, and failover strategy across model serving clusters
• Monitor and optimize latency, throughput, and cost across the inference stack
• Build observability tooling and incident runbooks for the platform team