AI Imaging Specialist - Radiology

LatchBio; San Francisco (CA); Remote; USD 140,000 - 180,000; Full time

Benefits offered by this job

Remote-friendly

SF office option

Job summary

LatchBio is building RadiologyBench to rigorously test AI agents on medical imaging data, including MRI, CT, ultrasound, and radiography. You will design evaluation tasks, define success criteria, and analyze how AI agents perform across organ systems.

The role blends radiology expertise with data scripting and AI critique in a fully remote-friendly environment. The position focuses on creating robust benchmarks, verifying image quality and acquisition, and validating agent outputs against

Qualifications

• Professional work with medical images; ability to read and interpret imaging data.
• Comfortable with Python for interpretation and data handling.
• Strong understanding of radiology modalities (MRI, CT, ultrasound or radiography).
• Ability to review AI outputs and assess clinical soundness.

Responsibilities

• Design the task and write questions radiologists ask in interpretation of images.
• Decide optimal answer formats and passing criteria for each case.
• Review AI agent performance and identify misses or non-existent findings.
• Collaborate with teams to define needed data and features for objective testing.

Skills

Python

Radiology imaging

AI in imaging

Artifact recognition

Tools

TCIA

MIMIC-CXR

UK Biobank

OpenNeuro

Job description

AI Imaging Specialist - Radiology

Latch builds rigorous scientific benchmarks (benchmarks.bio) for AI agents across biology. We work with frontier labs and pharma to measure whether agents can handle real biological workflows: the messy, multi-layer reasoning that matters in the field.

AI agents can now work through an imaging study the way a radiologist does: open the dataset, explore the dataset based on an indication, identify relevant features based on experience and tools and validate findings. Having agents being involved in the interpretation of clinical samples or even in the diagnosis of patients requires enormous care as well as validation of capability, but also offers massive advantages for patient care.

We're building RadiologyBench and are looking for people who work with medical images every day, whether you read studies or acquire them.

About the role.

You’ll decide what the right answer is for each case and build the studies that test it, from whether a scan was acquired properly to what shows. You then go through how AI agents actually handled them, including what they missed and what they reported that isn’t there. Labs use these results to see where their models fall short of an expert. The work covers MRI, CT, ultrasound and radiography, across organ systems.

Designing the task

• Write the questions that are frequently asked by radiologists or during interpretation of medical images
• Decide on the optimal answer format that the agent should use
• Decide what counts as a pass given the objective
• Review what agents are actually doing and if their approach holds up
• Help pick what is actually needed by the agent to solve the objective

Requirements

• Can work with medical images professionally and have handled thousands of studies, your role could include:
  • Radiologist, including trained outside the US (board-certified or equivalent)
  • Radiology resident or fellow
  • Sonographer (ARDMS or equivalent)
  • MRI or CT technologist (ARRT or equivalent)
• Deep experience in at least one modality (MRI, CT, ultrasound or radiography) and working familiarity with the others
• You know normal anatomy and common pathology for your area, and you can tell when the image itself is wrong: artifact, positioning, parameters
• Comfortable enough to work with python on interpretation and run scripts. No specific ML engineering is required but could come in handy
• AI-ready, daily use of popular agents like Claude Code, with judgement to distinguish between technical correctness but clinical unsoundness
• Bonus: imaging AI challenge experience ( e.g. RSNA, MICCAI, …) or contributions e.g. to Radiopaedia
• Bonus: familiarity with public imaging archives (TCIA, MIMIC-CXR, UK Biobank, OpenNeuro)

Culture @ Latch

We practice radical transparency: you’ll know how the company is doing, what’s working, and what isn’t. It’s always us against the problem, never each other. We’re opinionated but respectful of each other’s time, and we think through possible solutions before bringing a problem to anyone. We use AI constantly, so we reward original expert judgment, not AI output passed off as your own. You’ll start on the bench that fits your expertise and can move across teams as you build a track record.

Outside of work:

company outings most months, team off-sites, and a community that does cycling, soccer, figure skating, boxing, running, martial arts, music, books, and game nights.

Compensation & Logistics

Pay: $140K-$180K OTE (on-target earnings), with no ceiling.

• Your pay is your OTE times your weekly quota attainment. Hit quota, earn your OTE; double it, earn double. Example: $150K OTE at double quota = $300K.
• Your first 4 weeks (ramp) are paid at full OTE while we train you.
• You’re paid full OTE whenever quota can’t fairly apply: when a new project is starting, the platform goes down, or we pull you onto a special project.

In the US: full-time W-2

• Guaranteed base set by your state, paid every paycheck no matter what
• Health, dental, vision: 100% covered for you, 50% for dependents
• 401(k) (no match)
• PTO: 12 days to start, more as you’re promoted

Outside the US: contractor

• Paid on performance, with a monthly advance of 60% of OTE that’s never clawed back. US benefits don’t apply.

Growth:

• Individual contributor: six levels, so up to five promotions, with OTE rising at each one.
• Management: after your first promotion, you can move into managing a pod if that’s what you want.

Location:

fully remote is fine; onsite is preferred, at our Mission Bay waterfront office in SF with catered lunch and dinner and unlimited snacks.

Work authorization:

we sponsor H-1B (new and transfers), O-1, and TN, and support STEM OPT.

Interview Process

1. Apply. If your profile matches, we’ll send you a take-home project.
2. Take-home project (HackerRank). We review it as soon as it arrives.
3. Technical interview with a Member of Technical Staff (pod lead), scheduled right after your project review.
4. Culture interview with our C-suite.
5. Offer.
6. Background check, once you accept.