Genentech · posted · checked
Senior AI Engineer- Imaging
AWSKubernetesPytorchTensorflow$168k – $312kOn-site · San FranciscoSenior
Who can apply
On-site · San Francisco
Location: South San Francisco
We advance science so that we all have more time with the people we love.
As an imaging-focused machine learning engineer within the AI Enablement team, you will be working closely with folks that span the gamut across computational scientists, biologists, bench scientists, AI/ML experts, product leaders, software engineers, and everyone in between. Your work will help bridge scientific intuition with quantitative analysis, enable richer phenotypic analysis, and provide new multimodal capabilities across large-scale, state-of-the-art datasets. You'll build, own, and constantly improve scalable AI/ML and computer vision systems that unlock the potential of our diverse scientific imaging data (e.g., microscopy, digital pathology, biomedical imaging, etc), accelerating the discovery and development of life-changing treatments for patients.
The Opportunity:
Design, develop, and test robust, scalable, and maintainable AI/ML scientific web applications and backend pipelines tailored for high-throughput scientific imaging data processing and visualization.
Build, evaluate, and fine-tune state-of-the-art computer vision and deep learning models (e.g., cell segmentation, cell classification, phenotypic profiling, tissue segmentation, feature extraction, and image registration) applied to biological and clinical imaging modalities.
Build tools to evaluate AI/ML and vision model performance, establish benchmark datasets, and quantify model quality, robustness, and drift over time.
Partner with product managers, bioimage analysts, and research scientists to understand user workflows, shape requirements, and translate complex scientific imaging needs into actionable technical specifications.
Develop and maintain scalable cloud infrastructures and data pipelines for collecting, structuring, storing, and accessing large-scale multi-dimensional imaging datasets (e.g., OME-TIFF, Zarr, HDF5).
Optimize GPU memory footprint, batching, and inference throughput for large image pipelines and deep neural network models.
Contribute to architectural decisions, code reviews, and the evolution of engineering and MLOps processes for computer vision models.
Be willing to span the full stack and contribute where needed, even outside of core areas of expertise.