AI Biologist - Structural Biology

LatchBio • San Francisco, CA

3d

About The Position

Latch builds scientific benchmarks for AI agents across biology. The AI Biologist will serve as the scientific authority on ground truth for the Structural Biology team, evaluating whether AI agents can reason like expert structural biologists and distinguish what experimental data support from what a deposited or predicted model asserts. The role spans molecular systems, experimental and computational methods, and questions from structure determination to interaction analysis, molecular dynamics, and functional interpretation. The successful candidate will work with software engineers and scientists to build benchmark tasks and datasets involving viral and bacterial proteins, toxins, RNA elements, and host–pathogen complexes.

The role includes defining expert reasoning and writing gold-standard answers; designing realistic structural-workflow scenarios; curating datasets across experimental and computational modalities; and building Python analysis pipelines that compute verifiable ground truth from input files. The AI Biologist will also test agents for artifact recognition, adjudicate ambiguous evidence, select appropriate representations and comparisons, scrutinize reasoning, identify errors, and assess confidence and uncertainty.

Latch describes its culture as transparent, collaborative, respectful, and output-focused. Employees choose how they work, and the company values original expert judgment rather than AI output presented as one's own. New hires start on the benchmark suited to their expertise and may move across teams as they build a track record; people who perform well and bring leadership experience can move quickly into senior roles.

This is a 1099 contract (or W-8BEN internationally) with no end date. Pay is guaranteed during weeks 1–4 while ramping, then paid per certified task. Most people in the position earn $120,000–$180,000 or more, with uncapped upside. The commitment is full-time on the worker's own schedule; most of the team works 40 or more hours per week, with a few pod check-ins each week. The role may be remote anywhere, hybrid, or onsite in San Francisco; onsite is preferred. Onsite perks include catered lunch and dinner daily, a waterfront office in Mission Bay, and monthly parking when available. Work authorization is limited to US citizens, permanent residents, and OPT holders; the company cannot support STEM OPT extensions or sponsorship.

Requirements

• PhD in structural biology, biophysics, biochemistry, or a related field.
• Hands-on structural experience, including building and validating models and recognizing good and bad maps, models, and fits.
• Deep expertise in at least one of X-ray crystallography, cryo-EM, NMR/solution methods, or computational structural biology, and working fluency across the other areas.
• Ability to compute structural data such as contacts, superpositions, symmetry mates, map values, and geometry from files without a GUI.
• Daily use of Claude, Cursor, or similar AI agents, with the judgment to identify reasoning that is technically correct but scientifically unsound.
• Confidence to overrule an AI agent when evidence demands it, and openness to update when shown wrong.
• Ability to calibrate confidence and communicate uncertainty rather than defaulting to binary calls.

Nice To Haves

• Structural virology or antibody–antigen structural work, including viral glycoproteins, epitope mapping, or structural interpretation of escape.
• RNA structural biology or protein–RNA interaction analysis.
• Leadership experience, noted as relevant to moving quickly into senior roles.

Responsibilities

• Define what expert reasoning looks like for structural questions and write gold-standard answers with defensible scientific rationale.
• Design realistic benchmark scenarios across data collection and processing, map interpretation, model building, validation, assembly and state assignment, comparison, functional interpretation, protein–protein interaction analysis, molecular dynamics, and metadynamics.
• Curate datasets across X-ray structure factors and maps, cryo-EM maps and half-maps, atomic models, AlphaFold predictions and confidence metrics, molecular dynamics and metadynamics simulations and trajectories, NMR shifts and ensembles, SAXS curves, HDX-MS, cross-linking, and SHAPE/DMS reactivity.
• Build Python analysis pipelines using tools such as gemmi, Biopython/biotite, and numpy to compute verifiable ground truth from files provided to agents.
• Partner with software engineers to translate scientific judgment into new workflows.
• Test whether agents distinguish structural evidence from artifacts or over-interpretation, including unsupported ligands, register shifts, mirrored maps, crystal contacts mistaken for interfaces, misdocked domains, and misuse of B-factors or occupancies as evidence.
• Adjudicate ambiguous cases by determining what maps or measurements support, where experts may reasonably disagree, and what additional data could resolve the question.
• Evaluate whether agents choose the appropriate structural representation and comparison for a question, including biological assembly versus asymmetric unit, reference state, and domain for superposition.
• Interrogate agent reasoning step by step and challenge conclusions that would not withstand peer review or a validation report.
• Identify why an agent's reasoning fails, what an expert would do instead, and what evidence would change the conclusion.
• Score agent confidence and reward explicit uncertainty when structures are ambiguous.

Benefits

• Catered lunch and dinner daily for onsite employees.
• Waterfront office in Mission Bay.
• Monthly parking when available.
• Company outings most months, team off-sites, and activities including a run club, cycling, boxing, ice skating, and soccer.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: Ph.D. or professional degree