I build and ship AI systems end-to-end, from idea to production.
Focused on LLM systems, agents, and real-world deployment.
Recent Ships:
SpaceGuard: Orbital risk intelligence 🚀. A predictive intelligence platform providing real-time satellite collision risk assessment and portfolio monitoring.
OrphaNova: The OS for orphan drug R&D 🧬. An AI-native research engine architected to accelerate therapeutic discovery for rare diseases.
Homecastr: FaceTime for real estate 🏠. A conversational video AI that transforms static property listings into interactive, agent-led experiences.
Lastline: Lastline takes a pull request and turns it into a reviewable QA video for the team. PR → QA → Video → Chat → Feedback
Lead AI Engineer · OrphaNova
Building OrphaNova, an AI research system for rare disease discovery. Designed a 7-stage pipeline that retrieves biomedical literature, extracts disease-gene relationships, predicts protein structures (AlphaFold2), screens drug candidates (RDKit), performs molecular docking (Chai-1), and generates publication-ready research reports.
Research Assistant · Yeshiva University
Developed deep learning models for cardiomegaly detection from veterinary X-rays, achieving 85.75% accuracy on 2,000+ images. Built OrphanAtlas, a rare disease research platform combining GPT-based retrieval pipelines with biomedical datasets, now used by 500+ researchers.
Received Outstanding R&D Award at the Yeshiva University Research Symposium. Featured in YU News
Featured builds, shipped and live
Real-time orbital risk intelligence platform tracking 800+ satellites, conjunction alerts, critical portfolio exposure ($2.4B at risk), and active risk mitigation. Built for space industry professionals and operators.
AI-native research engine for rare-disease discovery: literature retrieval, disease-gene extraction, AlphaFold2 structures, RDKit screening, Chai-1 docking, and publication-ready reports.
Conversational video AI that turns static listings into interactive, agent-led experiences. Built with Tavus Phoenix and ElevenLabs for real-time video and voice.
AI wingman dating product: answer a few questions, launch a chaotic public agent that pitches you, roasts competition, and escalates as your deadline approaches.
Turns pull requests into review-ready evidence. Generates a guided QA walkthrough of the actual product experience, stitches it into a single review video, and routes feedback back into the team loop.
Continual learning agent for Kalshi prediction markets. Learns from new market data in real-time, generates trading signals, and executes trades with built-in risk controls and backtesting framework.
Agent-based generative AI workflows for drug repurposing research. Mines biomedical literature, extracts evidence, and generates hypotheses. Built with LLM + RAG pipelines and domain-constrained prompting to reduce hallucinations in sparse data.
Deep learning pipeline combining LSTM time-series analysis with FinBERT sentiment from news/social media. Achieved 15% higher accuracy than single-modality models. Includes backtesting and financial metrics (Sharpe ratio, MSE, RMSE) for risk-adjusted insights.
Built reinforcement learning agents using Q-learning, Deep Q-Networks, and Monte Carlo Tree Search. Implemented epsilon-greedy exploration and policy gradients. Secured 7th place globally (top 0.5%) through hyperparameter tuning and reward shaping.
Pinned repositories from GitHub.
Top publications from ResearchGate.
Visit ResearchGate ProfilePython, TypeScript/JavaScript, FastAPI, REST APIs, Node.js
PyTorch, TensorFlow, LLMs, RAG, agents, embeddings, multimodal, FAISS
AWS, GCP, Docker, CI/CD (GitHub Actions), Linux, infra automation
PostgreSQL, MongoDB, Firebase, streaming pipelines, time-series data
React, Next.js, dashboards, map/geospatial UI, Vercel
Satellite tracking, conjunction/risk pipelines, orbital telemetry, SSA tooling
Pick a date and time below to book directly.
Phone
+1 551 362 9944Location
NYC / San Francisco
