I build things
that learn
Hi, I'm Riddhima Medatwal! CS at Rutgers, Cornell Tech AI fellow. Working on applied machine learning across domains like robotics, genomics, and NLP.
Technical Stack
Regime classification in dynamical systems, transformer-based sequence models on fungal genomes, NLP for misinformation detection — full pipeline in Python, C++, TypeScript, and more.
Projects
Latte Art Robot
SF Hackathon
Taught a robot arm to pour latte art through physical demonstration at a hackathon in San Francisco. Learning from demonstration pipeline for precise fluid pouring motions.
Claryn
~90% less manual tuning
Autonomous ML agent built at the OpenAI NYC Hackathon. Trains, evaluates, and compares multiple models end-to-end with a retraining module that improves baseline accuracy by up to 12%.
Multi-Agent Debate
Real-time verification
Coordinated multi-agent system where AI agents debate claims using shared context and role-based reasoning. Real-time fact checking and source verification across agent responses.
Embedded Conv. AI
~60% faster response
Real-time conversational AI on a small embedded device (ESP32) that generates personalized spoken stories. Fast response pipeline delivering spoken output in under 3 seconds.
FreshShelf
70% less manual input
iOS app for voice-based food expiration tracking using speech recognition. Reduces manual interaction for pantry management.
Timeline
Experience
Undergraduate Researcher
Robotics ML. Building models for regime classification in high-dimensional dynamical systems.
Undergraduate Researcher
Computational genomics. Transformer-based sequence models for fungicide resistance prediction in fungal genomes.
Machine Learning Fall Fellow
NLP for misinformation detection. Built transformer pipelines across 170K+ news articles. Improved accuracy by ~20% and reduced test cycles by 35%.
Cornell Tech ML Fellow
Applied ML. Building production pipelines with industry partners through Cornell Tech.
Programming Team Lead
Competitive robotics. Leading programming for competition robots. 1st place NJ, 22nd internationally at VEX Worlds 2025.