About
Studying for an MSc in Computational Statistics and Machine Learning at UCL and researching causal ML at the Gatsby Computational Neuroscience Unit. Previously: 3+ years shipping AAA games at Electronic Arts, Relic Entertainment (SEGA), Microsoft Xbox, and Ubisoft.
Open to positions in ML and research.
Research
- Causal Inference for Structured Outcomes. MSc thesis at the Gatsby Unit, supervised by Houssam Zenati and Arthur Gretton. Training deep kernels to maximise the test power of counterfactual two-sample tests on structured outcomes (images, graphs, text).
- LLM-Guided Autocurricula via Semantic World Model. Supervised by Ahmet H. Güzel. Text-conditioned DiT world model with CLIP embeddings and LLM-driven autocurricula in dreamed environments; sample-efficiency gains over prioritised level replay.
- Latent Dynamics for Long-Horizon Consistency in World Models. Supervised by Jagmohan Chauhan. State-space JEPA world model learning 3D scene representations from multi-view inputs.
News
- 02/2026: Started my Master's thesis research on causal inference at the Gatsby Unit.
- 01/2026: Featured on the UCL Computer Science Spotlight series.
- 12/2025: Started research on long-horizon consistency in World Models supervised by Jagmohan Chauhan.
- 10/2025: Co-Heading the Machine Learning Tutorials series for the UCL Artificial Intelligence Society.
Projects
-
-
-
Pico-Banana
A PyTorch implementation of a Denoising Diffusion Probabilistic Model (DDPM) trained on FashionMNIST.
Python, PyTorch
[Code] -
Cart-Pole RL Agent
A reinforcement learning agent built from scratch in C++, trained on the cart-pole environment.
C++
[Code] -
Tiny-LLM
A lightweight transformer-based language model implementation in PyTorch.
Python, PyTorch
[Code] -
CUDA-Accelerated Raytracer
A high-performance GPU-accelerated raytracer built with CUDA and OpenGL.
C++, CUDA, OpenGL
[Code] -
Debris Disk Renderer
A C++ 3D rendering engine for visualizing and simulating debris disks around solar systems.
C++, OpenGL
[Code]