Jane Street Applied ML Puzzle
"Puzzle"
Jane Street Applied ML Puzzle
"Dropped a Neural Net"
Kyle Lukaszek
Summary
Hi, I'm Kyle. I like machine learning, computer graphics, programming language theory, and solving puzzles.
I'm finishing an M.Sc. in Computer Science at the University of Guelph, where my thesis focuses on efficient, interpretable self-supervised models of human visual perception and what we can learn from our eyes.
Outside of my research, I have worked on Kiln, my Rust-based render hardware interface for Vulkan 1.3 and Metal 4. It powers Spectra, my toy spectral path tracer that I work on for fun. I have also worked on Transformer-NES, an analytically constructed MoE transformer that emulates the NES's CPU and RAM, capable of driving a fully playable NES emulator. I also maintain Haskell bindings for the SDL3 library from time to time.
Languages
GPU APIs
Libraries
Tools
hover / tap for a surprise
Achievements
Publications
GI '26: Graphics Interface, Waterloo, ON, Canada
GI '24: Graphics Interface, Halifax, NS, Canada
Projects
MoE transformer-based NES emulator analytically constructed from the 6502 ISA, written in C++26 and Python.
- Developed an analytic weight compiler and MoE runtime with O(1) attention, driving a fully playable NES emulator.
- Built a native C++ NES emulator around the transformer CPU and RAM, including the PPU, APU, system bus, DMA, controllers, cartridge loading, and NROM and MMC-family mappers.
Render Hardware Interface for Vulkan 1.3+ and Metal 4, written in Rust.
- Designed an RHI supporting acceleration structures + compute, mesh, vertex, and pixel shader pipelines.
- Powers Spectra, my compute-based spectral path tracer for USD scenes.
Neumours
Implicit Neural Tumor Representations, written in JAX and Slang.
- Built an INR glioma segmentation model on BraTS 2023+ with Fourier positional encodings, reaching 0.823 Whole Tumour Dice (92% of nnU-Net) with 118× fewer parameters and 20× faster inference.
- Implemented a Slang-based differentiable raymarcher for visualizing INR tumour segmentations.
Maintaining Haskell bindings for the SDL3 native application development library.
- Authored 30+ cross-platform GPU rendering examples spanning Vulkan, DX12, and Metal.
- Authored several other examples for the many other features that SDL offers.
High-performance GPU-accelerated browser applications.
- Built a real-time LiDAR renderer handling 100M+ points on SensatUrban, plus GPU-accelerated colour-space, scene-graph, and interactive SDF geometry applications in the browser.
A WASM32 build of Google's Tint shader compiler and SPIRV-Tools.
- Ported the WGSL and SPIR-V portions of Tint and SPIRV-Tools to WASM32 for browser use.
- Exposed JavaScript and C++ APIs for browser-side shader cross-compilation, with the same runtime available as a static library.
Experience
Teaching Assistant
CIS*2750, CIS*3090, CIS*3110 · University of Guelph
Jan 2025 – Dec 2026
- Parallel Programming (CIS*3090): Returning for F26 after teaching Pthreads, OpenCL, MPI, and CUDA in F25 labs.
- Operating Systems (CIS*3110): Taught weekly labs on Unix/bash, scheduling, concurrency, and paging.
- Software Systems Development (CIS*2750): Supported instruction in C systems programming, CPython FFI, and SQL.
Research Assistant
HCI: Hardware & Statistical Modelling · University of Guelph
Jan 2024 – Jan 2025
- Developed a cross-platform driver for a JETI Spectraval 1501 spectrometer, replacing a Windows-only FTDI workflow and reducing experiment iteration time by over 50% while retaining full instrument accuracy.
Research Assistant
NLP: Pre-training & Post-training · University of Guelph
May 2023 – Sep 2023
- Built statistical and NLP pipelines for a large Twitter corpus, engineering psycholinguistic, sentiment, personality, and behavioral features across thousands of users.
- Trained/fine-tuned LSTMs and Transformer models with CUDA/PyTorch and performed time-series and causal analyses using ARIMA, stationarity testing, and statistical effect estimation.
Education
M.Sc. Computer Science
University of Guelph
Supervised by Dr. Denis Nikitenko and Dr. David Flatla. Research focus on perceptual colour science and inverse problems.
Coursework
Honours Bachelor of Computing
University of Guelph
Area of Application in Mathematics. Dean's List 2023 & 2024. Research Assistant under Dr. Denis Nikitenko and Dr. David Flatla.