Build the high-performance services and runtimes behind production AI agents - low-latency inference paths, data pipelines, and the platform glue that everything sits on.
About the role
We're building the runtime layer that powers production AI agents inside CosX customers - from lending platforms to retail intelligence. Rust is our weapon of choice for the parts that need to be fast, correct, and survive real production load.
You'll own services end-to-end: design, ship, monitor, and tune. The work spans inference orchestration, high-throughput data pipelines, and the integration surface between agents, internal tools, and customer systems.
What you'll do
What we're looking for
Nice to have
A few quick details and a link to your work. We respond within one week.