Scientist III – AI Scientist for Quantitative Neuropathy and ML Scalable Infrastructure

The Allen Institute accelerates science for a healthier world through large-scale research designed to answer some of the most complex questions in biology. Our multi-disciplinary teams generate foundational knowledge, tools, and data to understand how our brain, cells, and immune system work. We share our work openly so others can build on it, move faster, and ask bigger questions. We drive discovery forward and create new possibilities for improving human health.

• Develop and deploy large-scale ML models integrating multimodal neuropathological data, including digital histology, spatial transcriptomics, MRI, and clinical metadata, to characterize brain disease progression at cellular resolution
• Design and apply computer vision architectures (ViT and related models) and foundation models to quantitative neuropathology image analysis
• Design, build, and maintain scalable data pipelines that render diverse biological and neuropathological datasets, including gigapixel whole-slide images and spatial omics, ML-ready across cloud and on-premises GPU infrastructure
• Implement and optimize distributed training and inference workflows for foundation models, including multi-GPU and multi-node training, experiment tracking, and reproducible model versioning
• Apply Bayesian statistical and causal modeling approaches to describe and predict neurodegenerative disease trajectories
• Collaborate with scientists, computational biologists, neuropathologists, and software engineers within the Allen Institute and with external partners to advance model development from research to scientific impact
• Promote open science through publication of peer-reviewed papers and release of open-source code, models, and reusable ML tooling

*Note: Reasonable accommodations may be made to enable individuals with disabilities to perform the essential functions. This description reflects management’s assignment of essential functions; it does not proscribe or restrict the tasks that may be assigned.

• Ph.D. in Computer Science, Applied Mathematics, Computational Biology, Computational Neuroscience, Statistics, or related field; or equivalent combination of degree and experience
• Minimum of 5 years of postdoctoral or industry research experience
• Demonstrated ability to design, implement, and apply deep learning models to large-scale biological or medical image data
• Experience with Bayesian modeling and probabilistic inference
• Experience building and maintaining scalable data or training pipelines for large-scale ML workloads
• Proficiency in Python and ML frameworks including PyTorch or JAX, with strong software engineering practices (version control, testing, code review)

• 3-5 years of experience developing and applying ML methods to biomedical or neuropathological data
• Experience with digital pathology workflows, quantitative neuropathology, or computational histology
• Familiarity with multimodal data fusion approaches, including integration of imaging, omics, and clinical data
• Experience with score-based diffusion models, multimodal transformer architectures, or state-space models
• Experience developing or applying causal models of disease or biological processes
• Proficiency with cloud computing platforms and on-premises GPU clusters for large-scale model training, including distributed training frameworks (e.g., PyTorch DDP/FSDP, DeepSpeed, or Ray)
• Experience with containerization and workflow orchestration (e.g., Docker, Kubernetes, Slurm, Nextflow, or Airflow) and with large-scale image formats such as OME-Zarr
• Strong publication record of innovative individual and team scientific contributions
• Excellent written and verbal communication skills and ability to present complex findings to both technical and non-technical audiences

• Fine motor movements in fingers/hands to operate computers and other office equipment; repetitive motion with lab equipment

• This role is currently able to work both remotely and onsite in a hybrid work environment. We are a Washington State employer, and the primary work location for all Allen Institute employees is 615 Westlake Ave N.; any remote work must be performed in Washington State.

Travel

• Attendance and participation in national and international conferences occasionally required

• Include a cover letter with your application
• **Please note, this opportunity offers relocation assistance**
• **Please note, this opportunity may offer work visa sponsorship**
• This position is funded by and depending upon, a grant award to the Allen Institute. (The position may terminate at the conclusion of the grant)

$129,950 - $162,450 *

* Final salary depends on the required education for the role, experience, level of skills relevant to the role, and work location, where applicable.