About the RoleYou build what our partners use. Our models produce variant scores; you build everything between those scores and the scientist who needs to act on them.
The science team owns the model itself. You own the pipelines that run it on partner data, the interfaces people use to work with the results, and the evaluations that demonstrate how the scores hold up. Our inference infrastructure and core API are out of scope for this role.
You'll be paired with a product lead who owns a customer lane. You'll present your own work directly in partner meetings, which means fielding technical objections yourself. Expect to ship on a weekly cadence.
What You'll Do- Develop the application surface for your area of ownership, including interactive workbenches, variant scoring and ranking pipelines, and other tools that make model output usable by scientists unfamiliar with our API.
- Run our models on partner data and present results with enough interpretability for a computational biologist to trust the output.
- Build the evaluation infrastructure that makes our claims verifiable, including held-out benchmarks, blind retrospectives on solved cases, and head-to-head comparisons against tools partners currently use.
- Present your own work directly in partner meetings, field technical objections in real time, and return with fixes.
- Ship on a weekly cadence. Most features begin as prototypes developed live in partner conversations.
What We're Looking For- You build across the stack. Python for data and model work, TypeScript, React or similar for the interfaces.
- You have worked with real genomic data. VCFs, reference builds, variant annotation, and the specific ways this data is messy in practice.
- Comfortable engaging a partner's computational biology team as a technical peer, including in skeptical or challenging technical discussions.
- Comfortable operating without a finished spec, and able to take a rough direction and a partner conversation and turn them into a working system within a week.
Nice to Have- Experience designing model evaluations, and an opinion about what makes a benchmark honest.
- You've handled sensitive human data under strict access controls and understand the limits that comes with.
- A forward deployed engineering, solutions engineering, or founding engineer background at an AI or infrastructure company.
