A complete application in a minute
Tailored resume and cover letter, ready to send.
Braintrust is seeking a highly experienced researcher to design Linux-terminal benchmarking tasks grounded in scientific and clinical workflows. You will define criteria to judge reproducibility and accuracy, then document errors, uncertainty, and supporting evidence as part of a rigorous evaluation process.
Candidates should hold a PhD or MD with clinical specialization, with 7+ years of relevant experience (or 3+ years with three first-author or coauthor publications).
Help evaluate how AI systems approach scientific and clinical work. Use your subject expertise to design realistic problems, define verifiable outcomes and evaluate proposed solutions for scientific accuracy and quality of reasoning.
The project pays $1,350 per task, with an expected commitment of 20 hours per week for 1-6 months.