Life Sciences

Job Description

About the role

DataAnnotation is looking for experienced bench scientists to evaluate how frontier AI models handle real laboratory work: experimental design, assay QC, troubleshooting a failed run, reading raw instrument output, deciding whether data are usable. You bring the judgment you have built at the bench. We bring the model outputs that judgment is needed to grade.

In this role, you will design challenging, realistic tasks drawn from your own practice, such as a plate QC and go or no go call on a cell based assay, a flow panel gating review, a cloning strategy check, or a Western blot interpretation with the raw images, run them through frontier AI agents, and evaluate what comes back against a professional standard.

You will work with realistic professional files, the kind a scientist in your field actually handles: experimental data, protocols, records, reports and correspondence. Some you will assemble yourself; others will be provided. In every case the goal is the same: a task a competent scientist in your field would complete correctly and a frontier model currently gets wrong.

This is not a traditional lab or analysis role. You will be helping build better AI by putting your knowledge to work in a structured, flexible, fully remote environment. The work is long form and self directed, and clear written reasoning matters as much as technical depth.

Responsibilities

• Design challenging, realistic experimental biology tasks drawn from your own day to day workflows: the scenario, a prompt phrased the way you would brief a trusted colleague, and the supporting files an agent would need (plate maps and reader output, instrument exports, gel and blot images, flow summaries, protocols and SOPs, notebook entries, QC records, correspondence), using files you author yourself or files that are provided to you.
• Run those tasks through frontier AI agents and evaluate the deliverable they produce (the QC summary, experimental plan, troubleshooting memo, or results workbook) against the standard you would hold a colleague to.
• Compare two model outputs on identical prompts and files, decide which performed better, and document where each fell short.
• Write detailed grading rubrics that specify what a correct deliverable must contain, such as the right controls checked, the right wells excluded and the right diagnosis of a failed run, and explain in writing why a response passes or fails each one.
• Flag concrete failures with evidence: controls ignored or misread, edge effects and outliers missed, wrong normalization to a reference, a plausible sounding troubleshooting story the raw data contradict, fabricated values, ignored files, and off brief interpretation of the ask.
• Contribute across molecular and cell biology, protein biochemistry, immunology and flow cytometry, imaging and histology, microbiology and virology, in vivo and preclinical work, and laboratory operations and analytical sciences, and review and refine tasks built by other experts.

Domain qualifications

• 3+ years designing and running experiments at a pharma or biotech lab or an academic research lab (counted after undergraduate education).
• Depth of experience in at least one of: molecular biology and cloning; cell culture and cell based assays; protein biochemistry; immunology and flow cytometry; imaging and histology; microbiology or virology; in vivo and preclinical work.
• Working understanding of several of the other areas above, enough to know what those workflows involve and how they are run (for example, a protein biochemist who also understands how a cell based assay is set up and controlled, and how a flow panel is designed and gated), so you can assess work in adjacent areas and point out what was done correctly or incorrectly.
• You have designed and troubleshot experiments, not only executed established SOPs. You can explain what each control is for and diagnose why a run failed.
• You generate and QC primary data. You can look at raw instrument output and judge whether a run is usable before anyone makes a figure from it.

General requirements

• Master's or PhD, or a current PhD candidate, in Biology or a directly related field (molecular or cell biology, genetics, immunology, neuroscience, biochemistry, bioinformatics, or computational biology), completed in the U.S., Canada, Europe, or the UK.
• 3+ years of hands on experience in your subfield (see Domain qualifications above). Time in an academic lab or research institute counts after undergraduate education.
• Able to draw on your own real world experience and day to day workflows to craft scenarios that test whether an AI system can actually do the work.
• Hands on practitioner: you currently do (or recently did) the bench or analysis work yourself at an individual contributor level, not