Postdoctoral Fellow (Data Engineering & AI/ML)

About the Position

The Post-Doctoral Fellow I provides assistance to the Principal Investigator, Co Investigators, and Research Staff. S/he ensures enrollment numbers are successfully met, when applicable, and protocol adherence, monitoring visits, overseeing regulatory and administrative details, data management assistance and project close-out support is provided.

About the Project

This project is a multi-institution research collaboration with Stanford, Johns Hopkins, the Veteran Affairs (VA), and the Department of War (DoW) to build a sleep foundation model. Unlike traditional AI models, a sleep foundation model relies on self-supervised learning on vast amounts of physiological sleep study data (petabyte-level). By generating representations (embeddings) from the sleep data, the team aims to forecast future health risks and uncover latent patterns that traditional sleep scoring metrics miss.

Salary Range

$65,000 - $79,000. Salaries are determined based on several factors including external market data, internal equity, and the candidate’s related knowledge, skills, and abilities for the position.

Qualifications

• •PhD or MD required
• •1-2 years medical research project management experience strongly desired, preferably with Department of Defense
• •5+ years experience with multimodal data analysis

Proven experience with signal processing (eg, time-series biosensor data)

Hands-on experience with version control systems (eg, Git) and ability to work in a collaborative coding environment

Experience and/or a strong desire to learn the ins and outs of cloud computing, including managing cloud-native data warehouses and standing up ETL pipelines

Preferred qualifications: strong knowledge of sleep science, familiarity with machine learning workflows including model development, model tuning, and deploying models at scale

• •Ability to work in a fast-paced, multidisciplinary, multi-site (sometimes asynchronous) team environment
• •Knowledge of military system, preferred.
• •Demonstrate competence in oral and written communication
• •Must be organized, attentive to detail, and possess a positive, friendly and professional demeanor
• •Ability to be flexible with changing priorities and available to interact with employees, clients and sponsors of all levels
• •Ability to exercise independent judgment in fast-paced, high-pressured environment with strict deadlines and to manage multiple projects
• •Computer skills including at least intermediate level experience with Excel and other Microsoft Office Software

Responsibilities

Design, develop, and deploy scalable applications (both front-end interfaces and back-end data pipelines) to support large-scale research

Build ETL pipelines that ingest multimodal datasets (wearables, cross-referenced with EHRs, PSGs, and subjective sleep metrics), ensuring efficient storage, retrieval, and processing of massive datasets (+1million records)

Support the build-out of scalable infrastructure to support advanced machine learning models using physiological features and sleep microarchitectures

Optimize application performance and scalability through performance tuning, code refactoring, and database optimization techniques

Stay updated with emerging industry trends, academic literature, and technologies in data engineering, cloud architecture, and machine learning to continuously improve the lab’s technical capabilities

Ensure data integrity throughout engineering workflows. Assist in the preparation of Standard Operating Procedures (SOPs), analytical frameworks, and technical documentation

Maintain open communication with leadership, advise on technical processes, and curate progress reports

Provide technical support and oversight to team members with less experience

• •Assist in regulatory support, Data Sharing Agreements, and other project documentation
• •Collaborate and assist the Principle Investigator, Co-Investigators and research team in the performance the research study
• •Contribute to the drafting and submitting of abstracts, manuscripts and reports for dissemination
• •Prepare progress reports on research as required
• •Analyze and write-up data
• •Present complex information effectively to a range of audiences
• •Provide data management assistance
• •Provide project close-out suppo