Member of Technical Staff, Translational Medicine

Member of Technical Staff - Translational Medicine

Latch builds scientific benchmarks ( benchmarks.bio ) that measure AI performance in biology and medicine.

Frontier AI labs and pharma use them to answer one question: can an agent handle the messy, multi-layer reasoning that real biological work demands?

Every benchmark is grounded in real experimental and clinical work, including designing experiments, interpreting data, reading clinical endpoints, and advancing compounds. Each is built by scientists who've done that work themselves.

We're roughly 95 people in San Francisco, backed by Lux Capital, Coatue, Fifty Years, Haystack, Jeff Dean, Alec Nielsen, and George Church.

We're seeking a Member of Technical Staff to lead our Translational benchmark and define how the field measures AI in this domain.

About the Role

You will be latch's resident translational expert. Define benchmarks for translational medicine and determine whether a model’s answer is correct in accordance with how a physician, investigator, or regulator thinks.

What You’ll Do

Define benchmarks that measure whether agents can recover scientifically valid conclusions from translational and clinical data.

Turn drug programs and clinical-trial designs into objective tasks on which AI agents can be tested and graded. Failed trials are especially useful when the reason for failure is known.

Run cutting edge frontier agents at scale, testing them on the benchmarks you define, and QC'ing their output for scientific and technical accuracy.

Make clinically defensible decisions on behalf of our omics and therapeutics teams. Before Latch makes a clinical claim about a disease, you will be the final reviewer.

Build the clinical function at Latch, hiring and building a team around you.

Requirements

MD required, with demonstrated technical depth and experience in computational biology or bioinformatics.

You have worked with patients, been involved in a clinical trial, or made high stakes translational decisions.

You have dealt with or have a strong working understanding of FDA regulatory documents such as INDs or clinical trial protocols.

Preferred Qualifications

A technical degree in bioinformatics, computer science, engineering, math, or related.

Clear vision for how translational medicine can be turned into useful AI benchmarks.

Generally comfortable with AI agents and the use of computers. Able to resolve technical blockers and complete iterations with limited guidance.

Independently able to propose realistic, valuable tasks and build graders that stratify meaningful scientific errors

Experience building/leading a technical , hands-on team

Culture @ Latch

How we work. Genuinely flexible schedules— we only ask that you are extra communicative when you're coming in later than usual. We care most about hard work and output. We're respectfully opinionated, it will always be us against problems, never each other. We optimize for each other's time and bring solutions, not just problems.

Office & Perks. Waterfront office near Oracle Park, 2x free daily meals, unlimited snacks, company outings most months, and team offsites. Plus a vibrant Latch community: cycling, soccer, figure skating, boxing, run clubs, reading clubs, martial arts, music, game nights.

Compensation & Logistics

Full-time, in-person

Unlimited PTO (truly)

Work Visa sponsorship

Flexible Spending Account

401 contribution (no match)

Profit Share + Ambitious Equity

Team-wide science reading groups

100% covered Health, dental, vision

Relocation Assistance (if applicable)

Lunch and dinner provided every workday

Waterfront office in China Basin, San Francisco

Company-sponsored professional development

Flexible working hours, so long as you maintain an onsite presence

Best office dog: Nix

Interview Process

Intro Screen (30m): Recruitment Team

Intro Technical Screen (30m): Member of Technical Staff/CTO

Deeper Technical Screen (1hr): Member of Technical Staff/CTO

Onsite Work Trial: 2-3 days (we will take care of all accommodations)

Decision : 1-3 days after your interview