Skip to content
View ramlukn's full-sized avatar

Block or report ramlukn

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ramlukn/README.md

Nikhil Ramlukan

Software & research · Boston, MA

Undergraduate at Johns Hopkins — Chemical & Biomolecular Engineering and Computer Science, class of 2029. Software engineering intern at Dash Bio. Undergraduate researcher at Harvard Medical School (passive, phone-based detection of early neurological impairment, with Dr. Kee B. Park) and Johns Hopkins School of Medicine (machine-learning risk stratification after elective craniotomy).

nikhilramlukan.com — my site. It is a watch. Open it on a desktop.

Some things I've built:

  • Peel — a sub thirty-dollar optical dissolution tester that plugs into a phone, backed by an evidence engine that checks the pill against 22,000 recall records. The idea, the chemistry, and the classification layer were mine. HackMIT 2026 Grand Prize winner, and Elastic's first place. Submission.
  • GreenChain — ranks real manufacturers on emissions, transport CO₂, grid carbon, and climate risk. The backend — the models, the agents, the API — was mine. Won three tracks at HackPrinceton 2026.
  • Prophis — simulates public-health interventions across US counties. The data, the ML, and the statistics were mine.
  • BrainSentry — a stroke self-check demo on a phone, presented to the health ministries of Indonesia and South Sudan. I designed it and co-built it.

nikhilr.ramlukan@gmail.com · LinkedIn

Pinned Loading

  1. hackprinceton2026 hackprinceton2026 Public

    Forked from thejustjim/hackprinceton2026

    GreenChain — supply-chain emissions ranking. Backend, models, and agents were mine. Won 3 tracks at HackPrinceton 2026.

    TypeScript

  2. brainsentry_mvp brainsentry_mvp Public

    BrainSentry — phone-based stroke self-check demo, presented to the health ministries of Indonesia and South Sudan.

    JavaScript

  3. yhack2026 yhack2026 Public

    Forked from sophia-mai/yhack2026

    Prophis — public-health intervention simulation over US county data. Data, ML, and statistics were mine.

    TypeScript

  4. antibody-low-n-benchmark antibody-low-n-benchmark Public

    How much data do you actually need? A low-N benchmark for antibody property prediction: frozen ESM-2 embeddings vs cheap biophysical baselines, with cluster-held-out splits.

    Python