Join our evals team!

Benchmarking and training our tools is integral to rapid and robust AI development. We leverage human experts to help us assemble the data we need to build benchmark and training datasets, and are looking to grow our pool of expert researchers in various domains of biology.
‍
Responsibilities may include:
- Annotating or evaluating outputs from our AI tools.
- Generating or reviewing tasks for evaluating our tools.
- Completing evaluation tasks as human experts for baselining.
- Interacting with our tools in various capacities.

These activities span various aspects of the research process, including literature search, generating hypotheses, designing experiments, and analyzing results. You likely qualify if you:
- Have a PhD or Masters, or are pursuing either in Biology or a related scientific field.
- Can devote 5+ hours per week to working with us.
- Have an interest in driving the acceleration of discovery forward using AI.

Compensation: Please note that this is part-time contract (1099) work, not a full-time position. We use both per-task and hourly pay arrangements, depending on project specifics and expertise. In either case we aim for approximately $50 to $100 per hour equivalent.

If you'd like to register your interest, please fill out our interest form!