Ai Biologist - Peptide Discovery

LatchBio • San Francisco, CA

4d • $120,000 - $180,000 • Remote

About The Position

Latch builds scientific benchmarks for AI agents across biology and works with frontier labs and pharmaceutical companies to assess how agents handle real biological workflows. The AI Biologist will join the Peptide Discovery team and serve as the scientific authority on ground truth, evaluating whether agents can reason like expert peptide discovery scientists. The role focuses on interpreting raw selection, biophysical, and structural data; distinguishing genuine hits from artifacts; and assessing evidence as peptides advance from target to candidate.

Working with software engineers and scientists, the AI Biologist will develop tasks and datasets for benchmarks spanning linear, macrocyclic, and constrained peptides against protein targets, including protein–protein interactions. The work covers target tractability through candidate nomination, including defining expert-quality reasoning, creating gold-standard answers, curating data from real programs, and building Python analysis pipelines that produce verifiable ground truth.

The role also involves testing agents on difficult scientific judgments, including distinguishing signal from artifacts, reconciling conflicting evidence, weighing binding, function, potency, and developability tradeoffs, and identifying experiments that would resolve uncertainty. The AI Biologist will interrogate agent reasoning, identify where it fails, explain what evidence would change a conclusion, and score confidence with appropriate consideration of uncertainty.

Latch describes its culture as transparent, collaborative, opinionated but respectful, and focused on original expert judgment. Employees choose how they work and are evaluated on output. New hires start on the team that best fits their expertise and may move across teams. People who perform well and bring leadership experience may move into senior roles. The position is full-time, remote, hybrid, or onsite in San Francisco, with an preference for onsite work. It is a 1099 contract (or W-8BEN internationally) with no end date. 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.

Requirements

• PhD in peptide chemistry, biochemistry, biophysics, structural biology, medicinal chemistry, or a related field.
• Senior, hands-on peptide discovery experience, including personally analyzing real program data.
• Direct experience with at least one of the following: display selection (phage, mRNA, ribosome, RaPID, or DNA-encoded libraries); SPR/BLI or FP binding kinetics; binding-site mapping by structural MS or NMR; or peptide developability, including PAMPA/Caco-2 permeability or proteolytic and serum stability.
• Deep expertise in at least one area—display and selection, biophysics, structural mapping, or peptide medicinal chemistry—and working fluency across the others.
• Strong command of experimental design, quantitative data analysis in Python or R, and statistics.
• Daily use of Claude, Cursor, or similar AI agents, with the judgment to identify technically correct but scientifically unsound model 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.
• Must be a US citizen, permanent resident, or OPT holder; the company cannot support STEM OPT extensions or sponsorship.

Nice To Haves

• Peptide format and chemistry experience, such as macrocyclization, hydrocarbon stapling, N-methylation, D- and non-canonical residues, or HELM encoding.
• Target tractability or de novo design experience, such as PPI hotspot analysis, human-genetic evidence for therapeutic direction, or computational design with Rosetta or RFdiffusion.

Responsibilities

• Define what expert reasoning looks like for peptide discovery questions and write gold-standard answers with defensible scientific rationales.
• Design realistic benchmark scenarios across target tractability, hit generation, hit confirmation and kinetics, binding-site mapping, functional confirmation, and lead optimization.
• Curate datasets from real programs, including display-selection read counts, SPR/BLI sensorgrams, fluorescence-polarization titrations, affinity-selection MS, HDX-MS, crosslinking-MS, NMR chemical-shift perturbation, dose-response, permeability, and stability data.
• Build analysis pipelines in Python, including enrichment analysis and kinetic and dose-response fitting, to produce verifiable ground truth with tolerances that hold across replicates and fitting routines.
• Partner with software engineers to turn scientific judgment into new workflows.
• Test whether agents distinguish true signals from artifacts, including propagation or expression artifacts, aggregation or superstoichiometric binding in sensorgrams, and mistaken interpretation of HDX protection as direct contact.
• Adjudicate conflicting evidence, reconcile orthogonal binding-site datasets, assess competitive versus allosteric engagement, and identify experiments that would resolve uncertainty.
• Assess whether agents weigh tradeoffs among binding, function, potency, developability, added constraints, affinity, and other relevant properties.
• Interrogate agent reasoning step by step and challenge conclusions that would not withstand project review or lab discussion.
• Identify why agent reasoning fails, what an expert would do instead, and what evidence would change the conclusion.
• Score agent confidence, rewarding explicit uncertainty over overconfident conclusions on ambiguous data.

Benefits

• Guaranteed pay during weeks 1–4 while ramping up.
• Uncapped earning potential; most people in the position earn $120,000–$180,000 or more.
• Flexible scheduling: work on your own schedule.
• Company outings most months and team off-sites.
• Onsite catered lunch and dinner daily.
• Waterfront office in Mission Bay.
• Monthly parking when available.

What This Job Offers

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