About the job
Imaging based phenotyping of in-vitro biology is at the heart of insitro's efforts to accelerate drug development. At insitro, we use machine learning to derive clinically relevant insights from rich datasets generated in-house. As an Imaging ML Scientist, you will develop ML-empowered computer vision pipelines to extract insights about disease mechanisms from multiple microscopy modalities. You will be part of a cross-functional team of life scientists, software engineers, computational biologists, and machine learning scientists that strive to identify therapeutic targets and develop drugs of high efficacy and low toxicity.
Responsibilities
- Partner with experimental and computational biologists to design, troubleshoot, and optimize high-throughput imaging-based experiments and workflows
- Identify, understand, develop, and deploy novel computer vision and machine learning methods such as segmentation, feature extraction, and representation learning to extract features from microscopy image datasets
- Work closely with software engineers to build robust and well-tested image analysis workflows, able to be used by experimental and computational biologists with minimal direct support
- Calibrate analysis tools and workflows, define performance metrics, and conduct benchmarking to select fit-for-purpose solutions
- Communicate findings to cross-functional stakeholders through reports, visualizations, presentations, and publications
- Identify novel disease-relevant phenotypes and propose new screening paradigms that translate to actionable program decisions
Qualifications
Minimum
- Ph.D. in computer vision, machine learning, computer science or a related discipline, or equivalent practical experience (e.g., a Master's degree and 2+ years of relevant industry experience)
- Ability to communicate effectively and collaborate with people of diverse backgrounds and job functions on a daily basis
- Demonstrated ability to identify, understand, and find novel applications of state-of-the-art ML/CV methods from literature or other sources
- Strong programming skills in Python, including working with TB-scale image datasets and leveraging modern agentic software tools to accelerate development
- Experience developing models for diverse computer vision tasks (e.g. segmentation, recognition, classification, domain adaptation) including using modern deep learning frameworks (PyTorch, TensorFlow, Keras, etc)
- Extensive hands on experience working with microscopy data or similar biomedical or physical imaging modalities
- Passion for making a difference in the world
Preferred
- Demonstrated ability to write software in a team, industry experience or substantial involvement with open source projects.
- Experience modeling with video or imaging time-series datasets
- Experience with microscopy hardware, and/or image data acquisition in other contexts
- Understanding of optical physics, resolution, numerical aperture, etc.
- Familiarity with cloud computing services (e.g., AWS or Azure)
- Experience with database languages (e.g., SQL)
- Publication record of meaningful contributions to high-quality work in relevant computer vision, clinical ML, or biomedical venues