Pharmacist — Clinical AI Benchmark Review (Terac)

Terac is building clinical benchmarks for medical AI and needs practicing pharmacists to set the standard. You work through de-identified clinical cases and pharmaceutical product images on their remote platform, assess the data, identify the clinical markers that matter, and document your professional judgement as a written reference answer. A large part of the work is rubric development: turning standard clinical practice into scoring criteria that an evaluation pipeline can apply consistently, which is harder than it sounds because the criteria have to be specific enough to mark against without encoding one practitioner's habits. You also assess how various interpretations of the same medical data hold up.

Work is asynchronous against structured evaluation guidelines, so you set your own hours. Pay is $90/hr for services rendered, invoiced weekly. Contract work, fully remote.