Software engineer and tech enthusiast with 10+ years of experience building software.
Reasoning across hardware, software, and maths to solve messy, cross-disciplinary problems.
Focus
Artificial Intelligence
Generative, attention, segmentation, LLMs, and everything in between.
Computer Vision
Images, video, and what to notice in them. AI-powered or not.
Robotics
Machines that perceive, predict, and move together in the real world.
Graphics
Light, rendering, and real-time images.
Backend & full-stack
End-to-end products, distributed systems, and reverse engineering.
Videogames
Game engines, bots, networking and games built from scratch.
Toolkit
TypeScript
C++
Java
Assembly
Next.js
Three.js
Node.js
Ruby on Rails
Vulkan
OpenCV
TensorFlow
Unity
PostgreSQL
DynamoDB
NumPy
Polars
Docker
AWS
Ansible
CMake
Profilers
Bartending
TypeScript
C++
Java
Assembly
Next.js
Three.js
Node.js
Ruby on Rails
Vulkan
OpenCV
TensorFlow
Unity
PostgreSQL
DynamoDB
NumPy
Polars
Docker
AWS
Ansible
CMake
Profilers
Bartending
Python
Rust
.NET
React
WebGL
WASM
FastAPI
OpenGL
CUDA
ROS
PyTorch
Unreal Engine
MySQL
Redis
SciPy
Airflow
Kubernetes
Terraform
Git
Linux
Debuggers
Python
Rust
.NET
React
WebGL
WASM
FastAPI
OpenGL
CUDA
ROS
PyTorch
Unreal Engine
MySQL
Redis
SciPy
Airflow
Kubernetes
Terraform
Git
Linux
Debuggers
Selected Work
02
Research, games, and systems I shipped when the brief was fuzzy and the constraints were not.
01
TypeBind: native bindings for TypeScript
Built a toolchain for implementing a library once in TypeScript and running that same code on mobile through native bindings. Swift and Kotlin call natively, iOS and Android execute the same code.
Built an AI-native way to implement presentations as code. Slides are React you compose and own, so models can extend a deck the same way a person would, from the first slide through to the screen.
Audio-visual saliency prediction for 360° video via deep learning
Developed a novel, state-of-the-art, deep learning-based system to predict visual attention in immersive 360° virtual reality videos by combining both visual and audio cues.
Designed and developed a web-based SaaS platform that leverages AI to help users create personalized cover letters and resumes efficiently. The application features intelligent content suggestions, customization options, and seamless user experience to streamline the job application process.
Autonomous Drone Collaboration: Catch me if you can
Designed and implemented a drone coordination system using onboard stereo vision and predictive modeling. The multi-drone formation control algorithm enables a team of UAVs to estimate a ball's 3D trajectory and dynamically position themselves to catch it with a shared net.
C++ · ROS · Flightmare · Unity
06
Single scattering and direct illumination rendering using multidimensional control variates
Developed a novel light rendering solution that outperformed standard Monte Carlo methods by integrating Newton-Cotes quadrature as control variates, significantly reducing variance in illumination estimates in single-scattering scenarios.
Unsupervised and Semi-Supervised Learning for Bone Segmentation
Developed a deep learning pipeline for bone segmentation in spinal CT images using an unsupervised approach based on Active Contour Without Edges (ACWE) loss.
Python · Computer Vision · AI · TensorFlow
08
Top-down shooter: Counter-Strike 2D Remake
Developed a full remake of Counter-Strike 2D from the ground up, featuring smart AI bots for an engaging offline experience. Built a custom lightweight game engine using JavaFX, providing smooth gameplay and customization.
Online competitive first-person shooter: Call of Blocks
At age 16, I developed a competitive online first-person shooter featuring fully customizable, destructible environments and diverse game modes. Players can alter the map in real time, adding a dynamic layer of strategy and replayability.