Member of Technical Staff

LatchBio is building AI agents that do real biology. Agents that can take raw experimental data, run the right analysis, recognize when something is wrong, and return a defensible scientific claim. The hard part is defining what good analysis looks like across the assays and decisions that matter in real R&D, and building benchmarks that can tell when an agent is doing it right. You'll do three things: Define rigor. Translate the tacit workflow knowledge in your head into structured, reproducible analysis patterns with clear ground truth and known failure modes. Set the quality bar. Review agent outputs and engineer-built pipelines. Catch what looks right but isn't. Decide what an acceptable analysis looks like. Improve the agents. Generate reasoning traces, contribute training data, iterate with the model team on where agents fall down. You'll work directly with our CTO, head of product, and a small bioinformatics team. You will not be siloed. You will not be writing slides. Three tracks Apply to the track where you have the most depth. In your application, note your primary track in the cover letter or first line of your resume. If you span two domains, flag the secondary. Epigenetics End-to-end analysis of ATAC-seq, ChIP-seq, CUT&RUN/CUT&Tag, scATAC-seq, multiome, or Hi-C. You can explain why a peak opens, not just that it did. Therapeutics: End-to-end analysis of preclinical drug discovery data: HTS plates, dose-response curves, CRISPR screens, PRISM/DepMap/GDSC response matrices, ADMET panels, PK/DMPK. You know the difference between a real selective hit and broad cytotoxicity, and between a clean IC50 and a curve that shouldn't be reported. Single-cell: Personal end-to-end analysis of scRNA, snRNA, CITE-seq, spatial transcriptomics (Xenium, Visium, MERFISH, Stereo-seq), or Perturb-seq. You have intuition for kit-specific QC thresholds (you know 100K cells from a 10X run means something is wrong). You must have: 3-5+ years of hands-on primary analysis experience in one of the three tracks below Analyzed 3+ datasets in your domain with real consequences (publication, product decision, clinical or regulatory submission) Built or contributed to open-source tools, internal platforms, or production pipelines used by people other than you What we don't want People who supervised analyses but didn't do them Wet-lab scientists for whom the assay was a means to an end People who can describe a workflow but can't write the grading script for it Compensation $200k+ base depending on track and depth 100% premium covered Blue Shield platinum health ($0/$0) Free lunch and dinner Unlimited PTO Waterfront office, China Basin, San Francisco Hiring process Apply with resume and a few sentences on track + why Intro call with Saul (Technical Recruiter) or Kyle (COO) Take-home, designed by track (build a small benchmark task end-to-end) Technical with Kenny (CTO) Offer If you've ever wanted an AI that understands the data you've spent your career analyzing, come build it. #J-18808-Ljbffr LatchBio