I build AI systems and experiment with infra.
LinkedIn • open to collaboration and feedback
Rust fork of RL4Sys; Unstable Single-Agent Distributed Reinforcement Learning Framework written in Rust & exported to Python
Rust
Yet Another Reinforcement Learning framework designed in a system-centric way. Our goal is users can simply integrate this library to enable RL-based optimization to their key system component.
Emacs Lisp 5
LangChain/LangGraph assistant for identifying the most profitable margins between cryptocurrencies on different exchanges
Jupyter Notebook
Real-time chess recognition with Stockfish GUI suggestions
Propositional logic SAT solver for deterministic/stochastic expressions using Neo4J graph database & machine learning system optimization
Java 1
GAN-based imitation learning of user mouse movements