A complete application in a minute
Tailored resume and cover letter, ready to send.
Washington University in St. Louis seeks a senior data scientist to build, evaluate, and deploy statistical and ML models for brain data, including imaging and biomarkers.
You will collaborate with researchers and engineers, ensure reproducible workflows, and drive data quality across multi-site studies. The role requires leadership, strong Python, and experience in benchmarking predictive models and data harmonization within a secure research environment.
Location Remote, US Scheduled Hours 40
The Consortium for Brain Research and AI in Neurodegeneration (C-BRAIN) is an academic-industry consortium directed by Dr. Randall J. Bateman, Washington University School of Medicine in St.Louis. C-BRAIN brings together academic research institutions, pharmaceutical and biotech companies, technology partners, philanthropic organizations, and government agencies to develop AI-powered tools to accelerate discovery in Alzheimer's disease and neurodegenerative disorders. Washington University serves as the coordinating center for C-BRAIN. C-BRAIN is currently deploying initial versions of the tools and developing plans for benchmarking and evaluation of the tools in addition to platform integration and scaling. C-BRAIN is also working on development of foundational AI models for brain aging and neurodegeneration. See www.c-brain.org.
Build and evaluate statistical and machine learning models on spatial omics, brain imaging, biomarker, and clinical data, from strong baselines to deep learning, including cell- and tissue-level, biomarker, and disease-progression models.
Work with C-BRAIN's Senior Applied Scientist on foundation-model training data, downstream tasks, and embedding analyses that test whether models recover known biology, such as cell types, regional signatures, and age- and disease-related changes.
Combine data types across studies where it adds signal, including approaches that handle missing modalities and per-dataset expert models, such as tabular expert models trained separately on each contributor's trial, registry, or biomarker data.
Translate questions from researchers into analyses and models, and report results with clear limitations.
Serve as the team's hands‑on expert for at least one neuroscience data type (brain imaging, fluid and clinical biomarkers, or spatial omics), and apply working knowledge of spatial and imaging data pipelines across the others.
Judge raw and processed data independently: check instrument exports and study files for completeness (for example, images, segmentation and cell-level outputs, and scanner or assay metadata), identify artifacts and batch or site effects, and decide whether data are fit for modeling.
Specify what data providers must deliver (data dictionaries, units, assay, panel, and scanner versions, cohort criteria, identifier crosswalks, and QC flags), and follow up when deliveries are incomplete.
Check contributed data that C-BRAIN staff are not permitted to view: write automated validation and quality reports that run inside the protected environment and release only approved summaries, working from data dictionaries and synthetic data.
Harmonize data across sites, platforms, and assay versions, and confirm harmonization worked: known biological relationships hold and site cannot be predicted from the data.
Keep current with the literature and with collaborating groups' acquisition and processing methods, and adapt C-BRAIN pipelines and quality checks as methods change.
Build and maintain automated evaluation and benchmarking pipelines that every model and AI tool release must pass before production: versioned benchmark datasets, fixed held‑out sets, standard metrics, and clear pass/fail thresholds.
Design evaluations that hold up: subject-level and site-level splits, leakage and contamination checks between training and benchmark data, held-out cohorts, uncertainty estimates, and comparison against simpler methods.
Develop benchmarks with domain scientists that reflect real research tasks, including recovery of known biology, prediction tasks on spatial, imaging, and biomarker data, and expert-reviewed question sets for AI research tools.
Evaluate LLM- and agent-based research tools for answer accuracy, grounding and citation quality, and hallucination, using automated scoring checked against expert review, and compare candidate LLMs and agent configurations before the platform changes models.
Run regression testing across model, data, and provider versions; track performance, calibration, and robustness to site and batch shifts; and report results for release reviews.
Integrate evaluations into CI/CD and model release gates with C-BRAIN engineers, so every result is reproducible and tied to its model, data, and code versions.
Build reproducible pipelines from raw data to model-ready datasets: untouched raw copies, validation and profiling, harmonization, versioned curated data, and data dictionaries.
Write production-quality Python (and R where needed) with Git, code review, automated tests on code and data, pinned environments, and workflow tools such as Nextflow or Snakemake.
Run large processing and training jobs on high-performance and cloud computing using containers and schedulers such as Slurm, and track compute cost.
Use AI coding assistants to work faster while verifying generated code with tests and review.
Lead data and modeling work from day one: run working sessions, set data standards, and review analyses and code.
Mentor data scientists, postdoctoral researchers, and collaborators, and work closely with C-BRAIN engineers, wet-lab, imaging, and clinical scientists, and data contributors.
Maintain data catalog entries, lineage, and documentation so every dataset and result can be traced and reproduced, including the dataset descriptions shown to consortium researchers with each contributor's consent.
Provide technical input on data use agreement requirements (formats, transfer, storage, and permitted computation), follow consortium data agreements in all data handling, and apply disclosure checks (for example, minimum cell sizes) to summaries and aggregate results before they leave a protected environment.
Contribute to progress reports, Steering Committee materials, and publications in line with consortium review procedures.
Remote within the United States, per current Washington University policies.
Occasional on-site presence required for team meetings and consortium events.
Occasional domestic travel may be required for consortium events, partner meetings, or scientific conferences.
Standard office environment.
Primarily sedentary with standard computer use.
The above statements are intended to describe the general nature and level of work performed by people assigned to this classification. They are not intended to be construed as an exhaustive list of all job duties performed by the personnel so classified. Management reserves the right to revise or amend duties at any time.
Ph.D. - Doctor of Philosophy
No additional certification/professional licenses unless stated elsewhere in the job posting.
No additional work experience unless stated elsewhere in the job posting.
The salary range reflects base salaries paid for positions in a given job grade across the University. Individual rates within the range will be determined by factors including one's qualifications and performance, equity with others in the department, market rates for positions within the same grade and department budget.
If you are unable to use our online application system and would like an accommodation, please email CandidateQuestions@wustl.edu or call the dedicated accommodation inquiry number at 314-935-1149 and leave a voicemail with the nature of your request. All qualified individuals must be able to perform the essential functions of the position satisfactorily and, if requested, reasonable accommodations will be made to enable employees with disabilities to perform the essential functions of their job, absent undue hardship.
All external candidates receiving an offer for employment will be required to submit to pre-employment screening for this position. The screenings will include criminal background check and, as applicable for the position, other background checks, drug screen, an employment and education or licensure/certification verification, physical examination, certain vaccinations and/or governmental registry checks. All offers are contingent upon successful completion of required screening.
Washington University in St.Louis is committed to the principles and practices of equal employment opportunity. It is the University’s policy to provide equal opportunity and access to persons in all job titles without regard to race, ethnicity or shared ancestry, color, national origin, citizenship (where prohibited by federal law), age, religion, sex, sexual orientation, gender identity or expression, disability, protected veteran status, or genetic information. As a federal contractor, the university maintains affirmative action programs to implement its equal employment opportunity policy for individuals with disabilities and protected veterans, in accordance with Section503 of the Rehabilitation Act of 1973, as amended, and the Vietnam Era Veterans’ Readjustment Assistance Act of 1974 (VEVRAA), as amended.
Yes! After you create a Candidate Home account, you can set up and manage job alerts to be sent to you either daily or weekly, according to the filters you select. You can add, edit, or delete job alerts at any time. You will need to opt in to communications from WashU when you set up your first alert and will only receive alerts for jobs posted after the alert has been created. Set alerts today so you do not miss any new opportunities!
[Content placeholder]
[Content placeholder]
[Content placeholder]
[Content placeholder]
[Content placeholder]
[Content placeholder]