An RDKit wrapper treating molecular visualization as a software engineering problem, implementing strategy pattern for SVG generation with automatic raster fallback, native SELFIES support for generative AI workflows, and strict type safety for batch processing in molecular ML training pipelines.
A PyTorch testbed for the Müller-Brown potential energy surface, built as ground truth for ML-in-molecular-dynamics work. It pairs analytical and autograd force kernels (the analytical path compiled with torch.compile) with a BAOAB Langevin sampler validated against the canonical distribution and a two-tier test suite.
A digital restoration of Rahman’s seminal 1964 molecular dynamics paper using LAMMPS and a Python analysis pipeline featuring decorator-based caching, fully vectorized NumPy computations for O(N^2) operations, and modern tooling (uv, type hints, Makefile automation) transforming academic scripts into a reproducible research toolkit.
An end-to-end data factory for molecular machine learning that transforms raw chemical formulas (e.g., C6H14) into labeled 3D conformer datasets, using MAYGEN for structural isomer enumeration, RDKit for 3D embedding, and physics-based featurization to address data scarcity in computational drug discovery.
An input-to-analysis workflow for simulating adatom diffusion on FCC metal surfaces using LAMMPS and EAM potentials, covering copper and platinum to compare how atomic mass and bonding strength affect surface dynamics, with a Python analysis layer that generates energy and trajectory diagnostic plots. The LAMMPS setup is adapted from Eric N. Hahn’s adatom tutorial.
An automated GROMACS pipeline for generating molecular dynamics datasets suitable for machine learning, simulating capped dipeptides across nine residue types with 0.1 ps force-output resolution and atomic force extraction for training Neural Network Potentials.
A differentiable point-set alignment library implementing N-dimensional Kabsch, Horn quaternion, and Umeyama scaling algorithms with per-point weights, batch dimensions, and custom autograd across NumPy, PyTorch, JAX, TensorFlow, and MLX.
A PyTorch implementation enforcing strict Lyapunov stability guarantees on recurrent neural network controllers through Integral Quadratic Constraints, bridging 1990s robust control theory with modern deep reinforcement learning by solving semidefinite programs inside the gradient descent loop to provide mathematical certificates of safety.
A 2018 exploration of evolutionary algorithms applied to Atari games, forking Dennis Wilson’s d9w/CGP.jl, where my contribution was the Atari reinforcement-learning experiment layer (experiment variants, fitness functions, hyperparameter tuning) on top of the upstream Cartesian Genetic Programming framework and its NEAT-inspired speciation.
A sophomore year deep dive into functional metaprogramming, replicating FFTW’s genfft metaprogram logic in Haskell to generate straight-line optimized C kernels for FFTs, using symbolic DAG representation and algebraic simplification to understand how abstract algebra translates into efficient machine code.
A freshman-year automation tool solving the university scheduling constraint satisfaction problem through web scraping Drexel’s Term Master Schedule and implementing recursive backtracking algorithm to generate every valid schedule permutation satisfying user-defined hard and soft constraints, used throughout undergrad 2016-2020.
A ground-up PyTorch implementation of Word2Vec treating it as a systems engineering challenge, with “tensorized tree” architecture converting pointer-chasing Hierarchical Softmax into dense GPU operations, infinite streaming datasets with Zipfian subsampling, and torch.compile compatibility.
A computational social science project that built a 47,000+ bill dataset from Congress.gov (115th-117th Congresses), with a co-sponsorship legislative graph and TF-IDF baseline models for 33-class policy-area classification (up to ~0.89 weighted F1 on full text), now available on Hugging Face.
Research project that investigated how different NLP models perform on social media data, finding that domain-specific approaches often outperform large pre-trained models. Includes PyConversations, a Python module for analyzing conversations across social media platforms.
A 24-hour hackathon project exploring algorithmic musicology by using a webcam to scan a Rubik’s cube and generate audio based on color configuration, implementing first-principles waveform synthesis with byte-by-byte PCM generation and equal temperament frequency calculations to map visual entropy to harmonic resolution.
A wildly ambitious high school project (2014) to create a fighting game with 37 playable periodic table elements, assembling a team of artists and a composer to build a playable demo and launch a Kickstarter - teaching invaluable lessons about project management and creative collaboration despite the campaign’s failure.