Job Description

What You'll Do

As a contributor, you'll draw on your specialized research and published findings to stress-test advanced AI models. You'll design complex scenarios based on your own expertise to identify where models struggle with high-level scientific reasoning. By surfacing subtle reasoning errors and providing expert-validated corrections, you help set the standard that teaches AI to think more like a scientist. Your work ensures that the next generation of models is grounded in rigorous evidence and accurate technical logic.

Specialties We're Looking For

If your PhD is in a life-science field, there's likely a place for you. We're building depth across genomics, molecular and cell biology, immunology, neuroscience, biochemistry, medicinal chemistry, pharmacology, structural biology, microbiology, bioinformatics, physiology, and ecology and evolution (among others).

You're a Great Fit If

- You hold, or are completing, a PhD in a life-science field, or have equivalent research depth. - You can draw on your own published papers (work you authored or co-authored and already have accessible) as the source material for your Tasks. - You read primary literature fluently and think critically about study design, statistics, and evidence. - You have a precise, adversarial eye; you enjoy finding the exact point where an argument breaks and explaining it cleanly. - You're honest about uncertainty, distinguishing what the evidence shows from what you'd like it to show. No AI or machine-learning background needed. Your scientific judgment is the expertise we're after.

Materials You Can Use

Almost any piece of your work can seed a Task, for example: - Published papers - Figures and the data behind them - Result tables and summary statistics - Datasets and supplementary files - Experimental images and readouts - Sequences, structures, and other domain-specific data - Methods, protocols, and the analysis code behind them

Job Tags

Similar Jobs