About
Making systems make sense
I’m a software development manager who builds machine learning systems on the side that refuse to make unverifiable claims. My graduate work spans machine learning at Georgia Tech (MSCS, AI specialization) and business at BU Questrom (MBA); my undergraduate degree is in computer science, summa cum laude.
The thread through everything: comprehension. My cognitive science research measures when understanding breaks down. MedLit turns raw medical records into explanations patients can act on, with citations. mat73-reader opened an undocumented binary format to an entire research ecosystem. The day job is leading engineering teams through modernization, which is making systems comprehensible enough to change.
Where I’ve built
Biotech and drug discovery
Preclinical screening platforms, genomic and proteomic analysis tooling, and the AWS data infrastructure underneath them. High-throughput science runs on software that cannot lose a decimal.
Healthcare data
HL7 and FHIR integrations across clinics, PHI compliance, and now grounded language systems over clinical records. MedLit is not my first FHIR project; it is the first one I could publish.
Education technology
Large-scale learning management systems, LTI integrations, and build-versus-buy prototyping that saved real money. Learning platforms are comprehension engineering at scale.
Enterprise systems
SaaS compliance products, cloud migrations, and legacy modernization. Leading teams through systems old enough to have their own archaeology.
How I work
Evidence over adjectives
Systems I ship show where their claims come from: grounded retrieval instead of open-ended generation, deterministic code paths where correctness is non-negotiable, and measurements taken on outputs rather than assumed from intentions. The same rule applies to this site; every number on it comes from a repo, a paper, or a running system you can check.
Now
Current work
Retraining the cognitive load model on the real corpus its paper had to synthesize around, preparing that work for publication, and extracting MedLit’s validation layer into a standalone open-source tool. Getting to know the startup communities in Boston and Maine along the way.
See the work →