AI Neuroscientist

LatchBio • San Francisco, CA

8d

About The Position

Latch builds rigorous scientific benchmarks for AI agents across biology and works with frontier labs and pharmaceutical companies to assess whether agents can perform real biological workflows. The AI Neuroscientist will join the Neuroscience team as the scientific authority on ground truth, evaluating whether AI agents can reason like expert neuroscientists across molecular, cellular, circuit, tissue, and behavioral levels.

The role involves building benchmark tasks and datasets with software engineers and neuroscientists, spanning normal nervous-system function and disease. The successful candidate will define expert reasoning and write defensible gold-standard answers; design realistic research scenarios; curate multimodal data bundles; and create paired basic-science and disease tasks to test whether knowledge of normal function transfers to pathology. They will also evaluate model-system choices, adjudicate contested literature claims, interrogate agent reasoning, identify scientific errors, and assess confidence and uncertainty.

Latch describes its culture as transparent, collaborative, respectful, and focused on original expert judgment. Work is full-time on the contractor’s own schedule, with a few pod check-ins each week. The role can be remote, hybrid, or onsite in San Francisco, with a preference for onsite. The contract has no end date and uses 1099 status (or W-8BEN internationally). Pay is guaranteed for weeks 1–4 during ramp-up and thereafter is per certified task. Most people in the position earn $120,000–$180,000 or more, with uncapped upside. The company states it can work with US citizens, permanent residents, and OPT holders, but cannot support STEM OPT extensions or sponsorship.

Requirements

• PhD or MD/PhD in neuroscience or a closely related field.
• Hands-on neuroscience research experience, including first-hand data analysis and a publication record.
• Direct experience analyzing raw data in at least two listed modalities: electrophysiology, optical imaging, EEG/sEEG, neuroimaging, single-cell or spatial omics, neuropathology, or quantitative behavior.
• Deep expertise in at least one area—systems/circuit, cellular/molecular, clinical/translational, or computational neuroscience—and working fluency across system levels.
• Strong command of experimental design and statistics.
• Proficiency in using AI agents and the judgment to identify technically correct but scientifically unsound reasoning.
• Confidence to overrule an AI agent when evidence demands it, and openness to update when shown to be wrong.
• Ability to calibrate confidence and communicate uncertainty rather than defaulting to binary calls.
• Practical understanding of model systems, including iPSC neurons, organoids, rodents, NHP, and human cohorts.

Nice To Haves

• Familiarity with core resources such as Allen Brain Cell Atlas/BICAN, DANDI/NWB, OpenNeuro/BIDS, IBL, ADNI, PPMI, UK Biobank, and ClinVar/gnomAD.

Responsibilities

• Define what expert neuroscience reasoning looks like for research questions and R&D decisions, and write gold-standard answers with defensible rationales.
• Design realistic research scenarios spanning hypothesis and target selection, model-system choice, experimental design, data processing, and inference.
• Curate multimodal data bundles, including electrophysiology, calcium imaging, EEG/sEEG, MRI/PET, single-cell and spatial transcriptomics, histopathology, behavior, and biofluid markers.
• Pair basic-science and disease tasks to test whether understanding of normal nervous-system function transfers to pathology.
• Partner with software engineers to turn scientific judgment into new workflows.
• Evaluate whether agents choose appropriate model systems and units of analysis, and whether they recognize limits to translating findings from rodents, iPSCs, or organoids to human disease.
• Adjudicate contested claims in the literature by determining what the evidence supports, what it does not support, and which experiment could resolve the question.
• Interrogate agent reasoning step by step and challenge conclusions that are scientifically unsound despite appearing fluent or textbook-correct.
• Identify where agent reasoning fails, explain what an expert would do instead, and state what evidence would change the assessment.
• Score agent confidence, rewarding explicit uncertainty when evidence is incomplete.

Benefits

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

What This Job Offers

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