Chemist for AI Model Evaluation, Synthetic & Analytical Chemistry

Apply hands-on chemistry expertise to help develop and evaluate advanced AI models for scientific work. This part-time opportunity focuses on synthetic chemistry, reaction mechanisms, structure elucidation, and physical-chemical property reasoning, with work supporting a leading AI research team.

• Guide research and engineering teams in resolving chemistry knowledge gaps and improving model performance.
• Create challenging chemistry tasks, benchmarks, and training data that cannot be solved through simple search, including multi-step synthesis planning, reaction optimization, and spectroscopic characterization.
• Write accurate, well-structured solutions and evaluate model responses and step-by-step reasoning for chemical logic, tool use, and factual accuracy.
• Provide clear written technical feedback on model performance.
• Develop data specifications, grading rubrics, and verification processes for external technical teams, serving as a domain authority on chemistry-data quality.
• Advise on experimental design, common laboratory failure modes, and the chemical validity of outputs, including molecular representations such as SMILES.
• Work with other subject-matter experts to maintain consistency and accuracy across training data.

• PhD in synthetic, organic, medicinal, analytical, physical, or closely related chemistry, or equivalent research experience.
• At least 3 years of hands-on chemistry experience at a recognized pharmaceutical, biotech, chemical, materials, contract research, or university research organization.
• Experience designing and running multi-step small-molecule synthesis routes and optimizing reactions.
• Practical experience characterizing compounds using NMR, mass spectrometry, IR, HPLC, or LC-MS and interpreting the resulting data.
• Comfort using cheminformatics and scientific AI tools. Coding is not required.
• Strong written communication skills and the ability to explain complex technical decisions clearly.
• Preferred: experience with SMILES or SMARTS, grading-rubric development, benchmark design, or evaluation of scientific AI models or agents.

• Remote work, available to candidates based in London, UK, or the US East Coast.
• Part-time, hourly engagement with a minimum weekday commitment of 20 hours per week.
• The engagement is administered through an employer-of-record arrangement and may include placement on an AI lab''s extended workforce.

$70 to $100 per hour.

Employment decisions are made without discrimination based on race, religion, color, national origin, sex, pregnancy, childbirth, reproductive health decisions, related medical conditions, sexual orientation, gender identity or expression, age, protected-veteran status, disability, genetic information, political views or activity, or any other legally protected characteristic.