Founding Engineer (AI + Backend)

Founding Engineer (AI + Backend)

We're a team of researchers, engineers and theorists, in person in SF. You'll be building the benchmarks and the systems that run them.

Here are the broad themes that you’ll be working on

Benchmarks and evals design - designing domain-specific benchmarks from scratch: what to measure, how to ground it, and what makes a benchmark that an agent will continuously trust and pick from.

Continuously running large-scale autonomous eval systems - infrastructure that runs without a human in the loop: vendor APIs at scale, LLM-as-judge pipelines, scoring and metric computation, drift detection as models and products change underneath.

Research - understanding model behavior - why agents choose what they choose, and what survives their scrutiny. Adjacent to this you'll work on synthetic data generation, and problems like self-improvement code/software.

You'll build benchmarks & evals that the fastest-growing AI-first companies pay close attention to and produce continuous evals that their engineering teams care about.

If you want to do your life's work, reach out.

Apply to this role

VisaWill sponsor

Apply to this role

Equity0.30% - 0.80%