About
I am a Medical Doctor and Internal Medicine Resident, but I’ve always been a tinkerer at heart. My journey into tech started before medical school by rooting a Samsung Galaxy S3 without even touching a computer.
From breaking things to understand them, to editing magazines, to acting as the universal tech support wherever I go, I thrive on asking “why.”
Today, I build complex, vibe-coded digital tools using agentic AI, Docker, Linux environments and Google Cloud. I am a fast learner, easily distracted by fascinating new rabbit holes, and driven by the desire to build things that matter — whether in the physical world of medicine or the digital world of software.
My work sits at the intersection of medicine and artificial intelligence: I build clinical decision-support tools, fine-tuned medical language models, and research agents that apply large language models, retrieval-augmented generation, and AI agents to real problems in internal medicine and critical care — always with a deterministic safety layer between the model and the clinician.
Projects
ChartPilot
Python · FastAPI · Next.js · Google Gemini · FHIR
An autonomous pre-clinic chart-prep agent. Every night it reads a patient’s full FHIR record — labs, medications, diagnoses, allergies — and produces a one-page safety brief that surfaces the single critical detail a doctor might miss during a rushed two-minute chart review. It deliberately refuses the naive “FHIR → LLM → advice” pipeline: deterministic code owns every clinical fact (unit normalization, observation supersession, eGFR via CKD-EPI 2021, corrected calcium, anion gap, hyperkalemia risk), while the LLM may only propose findings and must quote verbatim evidence spans. Four deterministic citation gates reject any quote that doesn’t exist at the exact computed offsets inside a hash-frozen snapshot of the source (US FDA drug labels, PubMed), a blinded second model tries to falsify each finding, and a fail-closed final gate sends anything unproven or disputed to human review. It runs as a fully deployed nightly workflow on Google Cloud (Cloud Scheduler → Cloud Tasks → Cloud Run → Firestore) with least-privilege service accounts, surfacing results on a public read-only dashboard with clinician Confirm / Override / Correct controls.
View source on GitHub·Watch demo
TransBench
Python · LangGraph · MCP / Claude Science
A clinician-to-bench research agent, built as an MCP connector for Claude Science. You give it a bedside observation — say, an antihypertensive that seems to help an unexpected condition — and it returns a verified research brief: mechanistic hypotheses grounded in real, resolvable citations pulled live from PubMed, ClinicalTrials.gov and Europe PMC. An 8-agent LangGraph pipeline runs across Claude Opus 4.8, Sonnet and Haiku, and every hypothesis must clear three rigor gates — entailment, grounding and novelty — before it survives. When evidence is strong it designs a runnable single-cell experiment against a named public dataset; when evidence falls short it refuses rather than hallucinate one.
View source on GitHub·Watch demo
Iatronix
Python · FastAPI · Next.js · pgvector
A clinical reference tool for doctors. You type a clinical question and it fetches live data from FDA, PubMed, PMC, NICE, DailyMed, RxNorm and MedlinePlus in parallel, scores each source for evidence quality, then formats the result with Level of Evidence (LOE I–III) and Class of Recommendation (COR I–IIb) attached to every claim. It also includes a spirometry analysis module that classifies obstructive, restrictive and mixed patterns. A semantic cache (pgvector + Redis) returns repeated similar queries in ~200ms without hitting the LLM. Originally self-hosted in Docker containers, it now runs on Google Cloud Run.
View source on GitHub·Live site
StudyFeed
Kotlin · Jetpack Compose · Python · SQLite
A fully-offline, exam-agnostic study engine for medical exams. A Python “compiler” turns copyrighted source PDFs (past papers, question banks, textbooks) into a single versioned SQLite “content pack”, and a generic Kotlin / Jetpack Compose Android app plays any pack — learning its exam name, subjects, tags and every question at runtime from the pack’s manifest, with zero code changes. The whole design rests on one seam: the app is generic, the pack is the exam. All LLM cost is spent once, at build time — the compiler runs a resumable ~14-stage pipeline (unpack, de-duplicate, OCR, atomize-and-ground, corroborate across sources, past-paper trend analysis, a PageRank concept graph, deterministic 1–5 importance scoring over eight weighted signals, then grounded asset generation) through the Anthropic Batch API. The shipped APK reaches no network and runs no background work — not by policy, but because a Gradle “offline guarantees” plugin fails the build if an APK ever gains an INTERNET permission or a networking dependency. Every atom and every generated MCQ is grounded to its exact source page or quarantined, and builds are reproducible: content-derived stable keys mean a re-import never wipes your spaced-repetition progress (content and progress live in two separate databases). The app itself is a swipeable feed of five card types (MCQ, flashcard, reel, passage, interlink) scheduled by FSRS-6, plus thousands of pre-built topic dossiers, a walkable concept map, a blueprint-weighted mock exam and weak-spot drills. The first shipped pack is MRCP(UK) Part 1 — 32,957 playable items compiled from 99 source works. The public repo ships the tooling only; it never bundles exam content.
View source on GitHub
IatrogeniX
Python · Gemma 4 · LoRA / Unsloth
A fine-tuned medical language model built on Google’s Gemma 4 (2B parameter) architecture, trained on MedQA-USMLE and MedMCQA with LoRA adapters via Unsloth, then quantized to Q5_K_M GGUF for edge deployment. On top of the model sits a deterministic SafetyValidator that checks every output against a drug reference database (1,000+ entries) and ICU protocol rules before it reaches the user. Submitted to the Kaggle “Gemma 4 Good” hackathon; benchmarked against 20+ models and ranked #1 in the sub-10B parameter class with 83.1% accuracy on MedQA.
View source on GitHub
Aegis ETL
Python · FastAPI · Presidio · Ollama
An on-premise document ingestion pipeline. You drop files (PDF, DOCX, XLSX, CSV, MSG, EML, scanned PDFs via OCR) into a POST endpoint and it extracts text, detects and masks 20+ PII entity types using Presidio + spaCy, encrypts the original PII with Fernet before it ever reaches the database, generates 768-dimension embeddings via a locally-running Ollama model, and stores everything in PostgreSQL with a pgvector HNSW index. Search uses a hybrid RRF approach combining vector similarity, trigram distance and BM25 full-text scoring.
View source on GitHub
AbbrScan
JavaScript · Chrome Extension
A Chrome extension that detects medical abbreviations on research papers and shows their expansions in a sidebar. It runs automatically on PubMed, PMC and NEJM pages and does nothing on other sites. Detection uses three methods — dedicated abbreviation tables, inline “Full Term (ABBR)” patterns, and reverse “(ABBR) Full Term” patterns — each scored by confidence. Handles mixed-case forms like mRNA, IgG, siRNA and kDa, and can be toggled per site.
View source on GitHub
This Portfolio
React · Vite · Three.js · GSAP
The site this profile belongs to. A React SPA with two themes — a dark “terminal” mode and a light “clinical” mode that follows system preference but can be toggled. Smooth scrolling is handled by Lenis; animations and scroll-triggered effects use GSAP and ScrollTrigger. The “Rabbit Hole” section is a Three.js force-directed graph built from actual YouTube watch-history data, and the Contact section hides a fully working Tetris easter egg.
View source on GitHub·Live site
Experience
Internal Medicine / MRCP Candidate
Park Hospital, Gurgaon, India
2022 – Present
Managing complex internal medicine cases, high-acuity OPD, and inpatient medicine in a high-volume environment.
Medical Officer
Thane Civil Hospital, Thane, India
2021 – 2025
General Medicine and NCD OPD, managed COVID ICU workflows, and participated in various health camps.
COVID ICU Medical Officer
Bhiwandi COVID ICU, Bhiwandi, India
2021
Managed patients on ventilators, intubations and ABG analysis during the peak of the pandemic.
Medical Internship
Rajiv Gandhi Medical College & CSMH, Thane, India
2019 – 2020
Rotated through all clinical departments. Received the Best Medicine Intern Award (2020).