Day to day, that looks like: constructing RL environments around spreadsheets, documents, and professional workflows. Writing verification logic and reward functions. Working with domain experts to scope what a correct answer actually looks like in an LBO model or a clinical note. Some days it's engineering, some days it's closer to research. The common thread is that you're producing the ground truth that frontier models get measured against.
We build the evaluation datasets and RL environments that make AI reliable in domains where mistakes are expensive: finance, healthcare, and legal. Our team designs expert-curated training data, calibrated rubrics, and verifiable task environments for AI labs and startups pushing the frontier of what models can do in regulated industries.
We're a small, lean, London based team that moves fast and takes the work seriously. Everyone contributes directly. Initiative is rewarded, and ownership is the default. If you want to shape how frontier AI learns to operate in the real world, we'd like to hear from you.
Plata CardWorldwide
Pay not posted
Posted Jul 30, 2025
Pay not posted
Posted Jul 28, 2026
Qualified Health PBCPalo Alto, CA
$230K–$280K / yr
Posted 2 days ago
Surge AIUnited States - Remote
Pay not posted
Posted Jul 13, 2026
GoodfinSan Francisco, California
$200K–$300K / yr
Posted Jan 31, 2026
checked 2 days ago$130K–$185K / yr
Posted 25 days ago
Source: the Aptura Ashby job board. We last checked this job 4 h ago. We first saw it 8 days ago. A job on a job board does not always mean that the team interviews people now. We found this job board in a public list. We did not yet compare it with the careers page of the company.
No one has reported an interview at Aptura yet. Did you interview there? Add the questions.