Applied Machine Learning Engineer Extern

BRAIV

Mentors

Rabees Rafiq, Co-Founder & CTO, BRAIV

About Us

BRAIV is an early-stage healthtech company building an AI-native clinical decision support platform for psychiatric prescribers. Our platform uses machine learning trained on de-identified EHR data to deliver personalized treatment recommendations at the point of care, helping clinicians navigate trial-and-error  in psychiatric prescribing. BRAIV is a UChicago New Venture Challenge Top 25 Finalist and works in close partnership with UChicago Medicine.

Externship Description

This externship sits at the intersection of applied machine learning and clinical psychiatry. The extern will work directly with BRAIV’s technical co-founder/CTO to advance the core ML pipeline, conducting a systematic feature engineering study on a de-identified healthcare dataset from UChicago Medicine, with a reproducible model evaluation framework as the methodological backbone.

If you are interested in applying machine learning to real-world clinical data, building rigorous evaluation pipelines, and contributing to AI systems that have a direct impact on patient care, this externship will give you hands-on experience across all three.

Specific Objectives

Deliverable: A feature engineering study identifying which EHR-derived features are most predictive of psychiatric treatment outcomes, grounded in a reproducible evaluation pipeline (AUC, sensitivity, specificity, subgroup analysis) across de-identified clinical datasets.

What the extern will learn/work on:

– Feature selection and engineering on structured clinical (EHR) data

– Designing and implementing reproducible ML evaluation frameworks

– Applied model validation in a healthcare AI context

– Communicating technical findings to cross-functional audiences (clinical, product, business)

Training and structure:

– Weekly 1:1 check-in with mentor Rabees Rafiq (CTO)

– Standing invitation to BRAIV’s technical team syncs

– Ongoing collaboration with a multidisciplinary team spanning clinical, data science, and product

Additional outcome: Work may contribute to a BRAIV whitepaper or conference submission, with potential co-authorship opportunity.

Qualifications

This externship is best suited for a doctoral student (PhD) in Computer Science, AI/ML, Computational Biology, Bioinformatics, or a related field. Exceptional Master’s students may be considered. High proficiency in Python and foundational ML experience are strongly preferred. Familiarity with healthcare datasets, EHR data structures, or clinical applications of machine learning is a plus but not required.