Systems & Open-Source Engineering
From creating Teras (multi-backend tabular deep learning across JAX, PyTorch, and TensorFlow) and contributing random-sampling APIs to official Keras 3, to building Fontusfor multi-agent UAV recharging, porting Gemma 2 to Flax NNX (codriver), and writing a scalar autograd engine in pure C (micrograd_c).
01 / Open Source
Multi-backend frameworks, upstream contributions, distilled models, and low-level engines.
Created a Keras 3-based tabular deep-learning library supporting JAX, PyTorch, and TensorFlow backends. Implemented state-of-the-art research architectures (SAINT, TabNet, TabTransformer, FT-Transformer, CTGAN, TVAE, GAIN, PCGAIN) for classification, regression, data imputation, and synthetic-data generation.
Contributed Beta and Binomial random-sampling functionality (keras.random.beta, keras.random.binomial) and multi-backend consistency fixes to the official Keras 3 API across JAX, PyTorch, and TensorFlow.
Inspired by GitHub Copilot, built a custom 260M-parameter contextual code-generation model based on Google DeepMind’s Gemma LLMs. Ported Gemma 2 from Flax Linen to the NNX API and applied staged knowledge distillation—first using Gemma 2 2B on text (FineWebEdu) and then CodeGemma 2B on fill-in-the-middle code (CodeContests) across 8× H100 GPUs.
Implemented Andrej Karpathy’s micrograd from scratch in pure C: a scalar reverse-mode autograd engine and neural-network library exposing a PyTorch-like API.
02 / Research
Multi-agent reinforcement learning simulation environments and PyTorch evaluation code.
Custom PettingZoo Parallel multi-agent environment with vectorized NumPy dynamics and proximity-triggered aerial battery charging; trained parameter-shared IPPO/PPO policies in PyTorch and Ray RLlib and diagnosed a reward-hacking local optimum against an analytical baseline.
Open-source PyTorch implementation and reproducible multi-architecture evaluation harness for margin-bounded antidistillation sampling across CIFAR-10, CIFAR-100, and Tiny-ImageNet.
03 / Archive
Student and personal projects in computer vision, forecasting, and NLP (2021–2023).