AI Biologist - Biologics Development

LatchBio • San Francisco, CA

3d

About The Position

Latch builds scientific benchmarks for AI agents across biology, working with frontier labs and pharmaceutical companies to assess agents on real biological workflows. The AI Biologist will serve as the scientific authority on ground truth for the TxBench team, evaluating whether AI agents can reason like expert biologics development scientists. The benchmark focuses on monoclonal antibodies, Fc-fusions, and bispecifics between lead nomination and IND, including analysis of raw analytical traces and preclinical data, identification of genuine quality-attribute failures versus artifacts, and defensible advance, engineer, or kill decisions.

The role involves converting real development workflows into file-based tasks with structured outputs and deterministic grading; creating gold-standard answers and data fixtures; and working with software engineers and scientists to build benchmark workflows. The AI Biologist will assess agent reasoning, identify technical and scientific errors, determine what evidence should change a decision, and score confidence while rewarding appropriate uncertainty.

The role is full-time and remote, hybrid, or onsite in San Francisco, with work on the employee’s own schedule. The company prefers onsite work. Compensation is contract-based: pay is guaranteed for the first four ramp-up weeks, then paid per certified task. Most people in the role earn $120,000–$180,000 or more, with uncapped upside. Most of the team works 40 or more hours per week, with a few pod check-ins each week. The company limits work authorization to US citizens, permanent residents, and OPT holders; it cannot support STEM OPT extensions or sponsorship.

Requirements

• PhD in protein engineering, biochemistry, analytical chemistry, pharmacology, or a related field.
• Hands-on experience analyzing antibody development data; the candidate must have performed the analysis, not only supervised it.
• Deep expertise in at least one of analytical/CMC characterization, large-molecule DMPK, protein engineering and developability, or non-clinical safety, and working fluency across the other areas.
• Command of how readouts map to critical quality attributes, PK and effector properties, and release or comparability decisions.
• Python or R skills for data analysis, including chromatogram and electropherogram parsing, kinetic fitting, or PK modeling.
• Daily use of Claude, Cursor, or similar AI agents, and the judgment to identify model reasoning that is technically correct but scientifically unsound.
• 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 decisions.
• Eligibility to work under the stated authorization policy: US citizen, permanent resident, or OPT holder; STEM OPT extensions and sponsorship are not supported.

Nice To Haves

• Antibody format and Fc engineering experience, including IgG subclasses, YTE/LS, effector-silencing, or bispecific architectures.
• Familiarity with MAM, ICH Q6B/Q5E, FDA immunogenicity guidance, IMGT, SAbDab, and IEDB.
• Leadership experience; the posting notes that people who do well and bring leadership experience can move quickly into senior roles.

Responsibilities

• Turn real biologics development workflows into file-based tasks with structured outputs and deterministic grading, covering developability triage, analytical/CMC characterization, PK and FcRn reasoning, immunogenicity, effector function and safety, and first-in-human dose projection.
• Write gold-standard answers from raw data, accounting for real replicate, integration, and fitting variability.
• Curate data fixtures, including developability panels, glycan LC-MS, charge-variant CE, intact/subunit MS, SEC-MALS, FcRn/FcγR sensorgrams, concentration-time PK, and immunogenicity and effector assays.
• Partner with software engineers to translate scientific judgment into new workflows.
• Test whether agents distinguish genuine liabilities from artifacts, including co-eluting glycan peaks, misassigned charge variants, and assay flags not confirmed by orthogonal readouts.
• Test whether agents match effector function and affinity to mechanism rather than assuming that more is better.
• Test whether agents distinguish linear from target-mediated clearance and judge molecules against their target product profiles.
• Interrogate agent reasoning step by step and challenge conclusions that would not withstand a development review or go/no-go decision.
• Identify why an agent’s reasoning fails, explain what an expert would do instead, and determine what evidence would change the decision.
• Score agent confidence and reward explicit uncertainty over overconfident calls.
• Start on the benchmark team that best fits the employee’s expertise, with the possibility of moving across teams as experience builds.

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