Biologist for AI Model Evaluation

Use your Biology training to design and solve challenging problems that help fine-tune large language models. You will create clear, rigorous, step-by-step solutions, help define evaluation benchmarks across undergraduate to PhD-level biology topics, and collaborate with model researchers to probe and improve model reasoning in areas such as conceptual abstraction, multi-step reasoning, and data interpretation. Projects will also teach you how to leverage AI to become a stronger analyst.

• Design Biology problems and tasks specifically intended to test limitations of large language models.
• Produce high-quality, step-by-step solutions with clear and rigorous reasoning and explanations.
• Work with LLM researchers to align problem types and difficulty with evaluation goals, focusing on areas where models often struggle.
• Help create new evaluation benchmarks and item banks spanning early undergraduate through PhD-level Biology curricula.

• Strong foundation in Biology, at levels consistent with engineering entrance exams and graduate or PhD programs.
• Good research and analytical skills, able to decompose complex biological concepts into clear components.
• Excellent English comprehension and the ability to explain concepts plainly, using simple language, visuals, or simulations when appropriate.
• Ability to provide constructive feedback and detailed annotations on model outputs and problem solutions.
• Creative and lateral thinking for designing novel evaluation items.
• Self-motivated, able to work independently and collaborate effectively in a remote setting.
• Technical setup: reliable desktop or laptop and a stable internet connection.

• Pursuing or holding a Master’s, PhD, or postdoctoral degree in Biology, Biotechnology, Biochemistry, or a closely related field.
• Proven ability to analyze and solve complex biological problems using a structured approach.

• Location: Remote only.
• Engagement: Contractor assignment, freelancer status. This is contract work without paid medical leave or paid time off.
• Contract length and continuation: potential for extension based on performance and project needs.
• Opportunity to contribute to cutting-edge AI evaluation projects with leading language model teams.

• Candidates pursuing a Master’s, PhD, or postdoctoral research in relevant biology fields are eligible and encouraged to apply.
• Applicants must have the technical setup described above and strong English comprehension skills.