Biochemistry and Life Sciences Researcher for AI Model Evaluation

Help advance frontier AI models by bringing rigorous life sciences research judgment into task design, evaluation, and model improvement. You will work closely with an AI lab''s research and program management teams to ensure models can reason credibly about real scientific work, not simply produce plausible-sounding answers.

This senior, specialized role turns practical scientific expertise into high-quality instructions, reference solutions, benchmarks, and evaluation standards. You will work within the client''s tools using client-issued accounts and equipment, alongside research teams.

• Review life sciences knowledge-work tasks and model outputs for missing behaviors, weak reasoning, unsupported causal claims, mechanistic gaps, and conclusions that would not withstand peer review.
• Write detailed instruction specifications and golden solutions that establish accurate standards for life sciences problems.
• Create new tasks that reflect how life sciences research is conducted in practice.
• Design challenging evaluation sets and help develop domain-specific skills and tools with the research team.
• Calibrate standards with client researchers and adjacent-field specialists, translating expert scientific judgment into explicit, teachable criteria.

• PhD in biochemistry, molecular or cell biology, genetics, immunology, neuroscience, or a closely related life science field.
• At least 4 years of substantive research experience at a recognized research university, academic medical center, national laboratory, or industrial research organization. Graduate coursework alone does not qualify.
• Deep specialization in an area such as molecular and cell biology, biochemistry and structural biology, immunology and immuno-oncology, genetics and genomics, neuroscience, or systems biology.
• Senior-level progression, such as Senior Scientist, Staff Scientist, Research Scientist, Instructor, Principal Investigator, or faculty appointment, with meaningful ownership of research direction.
• Peer-reviewed publication record, preferably including first-author work in strong journals.
• Hands-on use of large language models in professional work and sound judgment in distinguishing rigorous answers from plausible but incorrect ones.
• Excellent written communication and the ability to provide precise, structured feedback.

• Full-time W-2 employment, 40 hours per week, with an initial 6-month engagement.
• Hybrid position based in the Bay Area, California. Candidates must live in the Bay Area and work on-site with the client team multiple days per week when required.
• This is not a remote role. Candidates who do not currently live in the Bay Area must relocate at their own expense before the engagement begins. Relocation assistance is not provided.
• This is a structured role integrated with an internal client team and standard enterprise workflows, rather than a freelance or project-based engagement.

$65 to $105 per hour.

Opportunities may be discovered through an online platform. Employment, onboarding, payroll, benefits, and compliance are administered by the employer of record.

Equal employment opportunity is provided without discrimination based on any legally protected characteristic. Reasonable accommodations are available for qualified individuals with disabilities and disabled veterans throughout the application process.