Latchbio
AI Biologist - Proteomics
San Francisco (preferred), Remote. Posted 13 days ago
The role
You will act as a scientific authority to test if AI agents can reason like expert mass spectrometrists. You will build tasks and datasets for proteomics, lipidomics, and metabolomics benchmarks and work with software engineers to develop new workflows.
What you will do
- Define expert reasoning for mass spec questions and write gold-standard answers
- Design realistic scenarios across sample prep, acquisition, identification, quantification, and biological interpretation
- Curate mass spec datasets across proteomics, lipidomics, and metabolomics
- Partner with software engineers to turn judgment into new workflows
- Test whether agents can tell true biological signal from batch effects, contamination, or artifacts
- Adjudicate ambiguous results
- Interrogate agent reasoning step by step
- Pinpoint where agents go wrong
- Score agent confidence
Required qualifications
- PhD in proteomics, analytical chemistry, biochemistry, or a related field
- Hands-on mass spectrometry experience with first-hand data analysis and a publication record
- Strong command of experimental design and statistics
- Daily use of Claude, Cursor, or similar agents
- Confidence to overrule an AI agent when the evidence demands it
Nice to have
- Mass spec experience beyond proteomics alone: lipidomics or metabolomics
- protein sequencing or antibody experience
Benefits
- Health, dental, vision: 100% covered for you, 50% for dependents
- 401(k) (no match)
- PTO: 12 days to start
- Catered lunch and dinner (onsite)
- Unlimited snacks (onsite)
- Company outings most months
- Team off-sites
Before you apply
- If your profile matches, we’ll send you a take-home project
- Background check, once you accept
- We sponsor H-1B (new and transfers), O-1, and TN, and support STEM OPT
About the company
Latch builds rigorous scientific benchmarks for AI agents across biology. They work with frontier labs and pharma to measure whether agents can handle real biological workflows.