AI Microscopy Image Analysis Engineer

Ontix Intelligence

Remote · $130k – $160k / year · Full-time · Posted 5 months ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

Senior Machine Learning Engineer (Tech Lead), Robot Learning, Loco- Manipulation Pathrobotics View →
Staff / Principal Full Stack AI Engineer Brighthire View →
Senior Machine Learning Engineer (Reinforcement Learning/World Model) Pathrobotics View →

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

Pharmaceutical companies spend $2M per compound just on microscopy analysis during drug discovery — most of it on a human expert scrolling through 40,000 cell images per experiment looking for phenotypic changes. We've built computer vision models that do the same analysis in 4 minutes. Now the bottleneck is generalization: each lab uses different staining protocols, microscope models, and cell lines, and each variation breaks the model. Your challenge is domain adaptation. How do you make a model trained on HeLa cells in Phase contrast imaging work on iPSC cells in fluorescence without retraining from scratch? How do you quantify uncertainty so researchers know when to trust the model and when to pull a human in? You'll design the adaptation strategy, build the uncertainty quantification framework, and validate performance across the 12 lab configurations our 8 pharma clients use. This is a research-leaning engineering role. We publish 1-2 papers per year and encourage you to contribute. You'll work alongside two computational biologists who understand the domain deeply and two engineers who handle platform infrastructure.

Fully remote.

Responsibilities

Design domain adaptation strategies for microscopy imaging across lab configurations
Implement uncertainty quantification to calibrate model confidence signals
Validate model performance across 12 different lab setups and cell line combinations
Build evaluation pipelines that compare AI analysis against expert annotations
Collaborate with computational biologists to encode domain knowledge into models
Contribute to research publications on microscopy AI

Requirements

5+ years in computer vision with focus on biomedical or scientific imaging
Experience with domain adaptation, transfer learning, or few-shot techniques
Strong PyTorch skills and familiarity with segmentation and detection architectures
Ability to work with small labeled datasets common in scientific applications
Publications or open-source contributions in computer vision preferred