Machine Learning Scientist I/II
E
E11 BioOptical connectomics
Alameda, CA, Open to RemoteFull-TimeMiddle
Salary$130,000 - $225,000 a year; Base Salary Range: $130,000 - $225,000; Bonus: Performance-based, up to 20% of base salary; 401k match: up to 6% of base salary; Total potential compensation range: $163,800 - $283,500
Apply NowOpens the employer's application page
Job Details
- Experience
- 3-5 years of relevant work or research experience
- Required Skills
- Machine LearningSoftware EngineeringComputer Vision
Requirements
- Hold a Ph.D. in computer science, machine learning, applied math, computational biology, or a related science or engineering field, or have a Ph.D.-equivalent publication history.
- Have 3-5 years of relevant work or research experience.
- Demonstrate a strong history of independently executing novel ML solutions.
- Have a strong background in computer vision and applying ML tools to large microscopy datasets.
- Have experience with software engineering best practices, such as version control and code reviews.
- Experience with graph-, sequence-, or point-based ML methods, such as GNNs, Transformers, or PointNets, is preferred.
- Experience processing large chunked data such as Zarr in AWS or GCP is preferred.
- Experience with large-scale connectomics data and tools such as Neuroglancer, WebKnossos, CAVE, or CATMAID is preferred.
Responsibilities
- Develop ML approaches for automatic proofreading of segmentations in large PB-scale optical connectomics volumes using shape and barcode information.
- Own scalable workflows for ingesting large connectomic datasets into WebKnossos and CAVE.
- Collaborate with academic and industry experts to build and extend tools for automated proofreading and interactive visualization.
- Develop and evaluate scalable pipelines for synapse detection and partner assignment using morphological and protein-labeling information.
- Build ML-based image-processing tools to address bottlenecks in data processing and analysis.
- Maintain laboratory science practices and communicate results through reports, presentations, and scientific documents.
- Process a new dataset end-to-end and identify improvements in segmentation accuracy and efficiency.
- Integrate graph-based automatic-proofreading methods into standard block-wise workflows for large optical connectomics volumes.
View Full Description & ApplyYou'll be redirected to the employer's site