Member of Technical Staff (Epigenetics, Therapeutics, Single-cell)

LatchBio•San Francisco, CA

3d•$200,000•Onsite

About The Position

LatchBio is building AI agents that do real biology. Agents that can take raw sequencing data, run the right analysis, recognize when something is wrong, and return a defensible scientific claim. The hard part isn't model training. It's defining what good analysis actually 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. In this role, you will translate tacit workflow knowledge into structured, reproducible analysis patterns with clear ground truth and known failure modes, review agent outputs and engineer-built pipelines, catch what looks right but isn't, decide what an acceptable analysis looks like, generate reasoning traces, contribute training data, and iterate with the model team on where agents fall down. You will work directly with our CTO, head of product, and a small bioinformatics team. You will not be siloed. You will not be writing slides. There are three tracks: Epigenetics, Therapeutics, and Single-cell. Apply to the track where you have the most depth and note your primary track in your application. If you span two domains, flag the secondary.

Requirements

3-5+ years of hands-on primary analysis experience in epigenetics, therapeutics R&D, or single-cell genomics.
Deep domain expertise in one of the three tracks (Epigenetics, Therapeutics, or Single-cell).
Ability to explain why a peak opens, not just that it did (Epigenetics track).
Fluent in tools like MACS, ArchR, Signac, ChromVAR, deepTools (Epigenetics track).
Ability to explain the difference between a real selective hit and broad cytotoxicity, and between a clean IC50 and a curve that shouldn't be reported (Therapeutics track).
Fluent in tools like scipy curve fitting, MAGeCK, RDKit (Therapeutics track).
Intuition for kit-specific QC thresholds (you know 100K cells from a 10X run means something is wrong) (Single-cell track).
Fluent in tools like Scanpy, Seurat, Cell Ranger, scVI, Squidpy (Single-cell track).
Ability to run a full analysis end-to-end in your domain, from raw platform output to a defended biological or therapeutic claim.
Ability to diagnose when an analysis is wrong.
Ability to justify every analytical choice.
Ability to write reproducible code in Python or R.
Comfortable in pandas/numpy/scipy and the standard tools of your domain.
Ability to translate your workflow into something someone else can grade.
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.

Nice To Haves

Personal end-to-end analysis of ATAC-seq, ChIP-seq, CUT&RUN/CUT&Tag, scATAC-seq, multiome, or Hi-C (Epigenetics track).
Personal 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 (Therapeutics track).
Personal end-to-end analysis of scRNA, snRNA, CITE-seq, spatial transcriptomics (Xenium, Visium, MERFISH, Stereo-seq), or Perturb-seq (Single-cell track).
If you span two domains, flag the secondary.

Responsibilities

Translate the tacit workflow knowledge in your head into structured, reproducible analysis patterns with clear ground truth and known failure modes
Review agent outputs and engineer-built pipelines.
Catch what looks right but isn't.
Decide what an acceptable analysis looks like
Generate reasoning traces, contribute training data, and iterate with the model team on where agents fall down
Run a full analysis end-to-end in your domain, from raw platform output to a defended biological or therapeutic claim.
Diagnose when an analysis is wrong.
Justify every analytical choice.
Write reproducible code.
Translate your workflow into something someone else can grade.