AI Biologist - SpatialBench-Long

LatchBio; San Francisco (CA); On-site; USD 120,000 - 180,000; Full time

Benefits offered by this job

2x free daily meals

Waterfront office near SF

Monthly parking

Job summary

LatchBio is seeking an Bioinformatics Engineer to join the Spatial team, testing AI agents on spatial transcriptomics projects and ensuring ripple effects are understood, not just mechanics. You’ll work at the frontier of AI in biology from a flexible, output-driven environment.

You’ll evaluate tissue alignment, segmentation, and deconvolution decisions, drawing from published papers and real data, with cross-domain learning and interoperability across teams.

Qualifications

• Must understand how image preprocessing affects segmentation and downstream analysis.
• Know trade-offs between spatial platforms and deconvolution vs segmentation.
• Be able to learn spatial tools and image-processing pipelines as needed.
• Design multi-checkpoint benchmarks and defend assumptions in variable tissues.

Responsibilities

• Design tasks that test AI agents on real spatial transcriptomics projects.
• Grade rationale behind segmentation thresholds and deconvolution choices.
• Build benchmarks handling registration failures and variable tissue morphology.

Skills

Systems thinking

Domain judgment

Tool flexibility

Task design

Tools

Baysor

STdeconvolve

giotto

Squidpy

Job description

AI Biologist - SpatialBench-Long

As molecular data generation and frontier model intelligence grows, new approaches to data analysis are needed across the biotech industry. Latch is building intelligent, high-performance agents for biological data analysis, empowering over 5,000 scientists across 150+ R&D labs to handle data from instrument-to-insights.

We're seeking a Bioinformatics Engineer to join our Spatial team, working at the frontier of what artificial intelligence can achieve in biology.

About the Role

You design tasks that test whether AI agents can work through real spatial transcriptomics projects. It's not about whether they can run a tool, it's whether they understand how decisions cascade. You pick how to align tissue images, which affects how you segment cell boundaries, which determines which unmixing method works, which shapes everything downstream. We're testing if they get that ripple effect. You'd be pulling from real published papers, building multi-stage tasks, and grading whether agents understand the why behind each choice, not just the mechanics.

Requirements

• Systems thinking across spatial workflows: You understand how image preprocessing (tissue alignment, background removal) affects segmentation quality; why nucleus-level segmentation demands different deconvolution (RCTD, Tangram, SPOTlight, STRIDE) than spot-level data; when morphological features matter for downstream inference

• Domain-specific judgment: You know the trade-offs between platforms (Visium's spots vs. MERFISH's near-cellular resolution vs. Xenium's high-plex imaging); when to deconvolve spots vs. when to segment first; how cell density and tissue morphology constrain method choice

• Tool flexibility: You learn spatial tools (Baysor, STdeconvolve, giotto, Squidpy) and image-processing pipelines as needed

• Task design: You build multi-checkpoint benchmarks where agents must handle registration failures, justify segmentation thresholds, and defend deconvolution assumptions in tissues with variable morphology

Culture @ Latch

How we work.

Genuinely flexible schedules, we just ask that you communicate 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, not each other. Optimize for each other's time and bring solutions, not just problems. You'll join a bench suited to your expertise, but we value cross-domain learning and interoperability across teams.

The office & perks.

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

Compensation & Logistics

• 1099 (or W8-BEN) contract, 40 hrs/week, no end date

• Fully performance-based pay: $120K–$180K, uncapped upside. 2x quota = 2x pay.

• 2-4 week paid ramp - full OTE from day one

• Remote (globally), hybrid, or onsite in SF (onsite preferred)

• Work authorization: OPT visa holders only (not STEM Extension)

• Onsite perks: 2x free meals/day, waterfront office (China Basin), monthly parking (based on availability)

• Candidates with all of the above qualifications + proven management skills will be eligible for more senior positions

Interview Process

Timeline:

We move fast: 8–12 days from submission to offer.

1. Intro Screen - Technical Recruiter

2. Take-Home Project - HackerRank

3. Technical Interview - Member of Technical Staff

4. Culture Interview - C-Suite (If applicable)

5. Offer