Projects

Pass@k is Not a Property of a Model

Python, PyTorch, verl, AWS, SkyPilot

Published first-author preprint on evaluating RL-trained LLMs & methods for training/testing; submitted to conference
Showed central results of Limit of RLVR (Yue et al.) fall 3x (36 to 12 pts) by altering the wording of the test questions
Evaluated that an ensemble of 3 independently trained Qwen2.5 runs beats one model by 6% at matched sample budget
Showed the main reasoning benchmark (MATH-500) is 98.8% solved by base models it tests, leaving 6/500 trials usable

Python, Neo4j, Qdrant, Claude API, FastAPI, Modal

Built a 5-stage agentic predictor for Polymarket, achieving 30.5% out-of-sample ROI on 950+ markets and 140+ trades
Architected a hybrid RAG pipeline over Neo4j & Qdrant via Reciprocal Rank Fusion with a BGE reranker
Beat or matched the market on Brier scores on the 53% of markets the model chose, validated across multiple evaluations
Caught 96% of hallucinated claims via a 4-dimension LLM judge pipeline to detect priming, recency, & confirmation bias

Python, PyTorch, ONNX, MediaPipe, Rust, TypeScript, Docker

Built a 2 player boxing game engine that tracks movement through your camera and simulates a boxing match, like a Wii
Designed an ML model to classify punches into 5 types (ex. jab, hook) at 80% accuracy & compressed it to run in browser
Architected the game engine using 33 tracked body points per player 60 times a second — works out from joint speed whether a hit landed and where, then runs damage with hit thresholds calibrated to each player's own reach and speed

Python, PyTorch Geometric, Gymnasium, FastAPI, AWS ECS

Built a production multi-agent RL system for Settlers of Catan using MAPPO with self-play, served via FastAPI on AWS ECS Fargate
Achieved a 74% win rate vs. random and 52% vs. rule-based agents (25% baseline) with a heterogeneous Graph Attention Network over a typed board graph
Built an autonomous research agent using UCB1 bandit selection to propose & promote hyperparameter configs, closing the loop with drift-triggered retraining

JavaScript, Gmail/Outlook OAuth2

Built an open-source bulk email sender with Gmail and Outlook OAuth2, CSV/XLSX input, rate limiting, and dry-run previews
13 stars on GitHub