AI Research Engineering · London
I build graph-wiring methods, spectral vector search, and agentic code-generation workflows — and ship them as open-source Rust and Python.
Selected work
The theoretical foundations, implementation, and empirical proof for each project.
A spectral latent diffusion model where decoding runs on the feature-space manifold defined by a frozen ArrowSpace graph Laplacian. A graph-structured decoder replaces unconstrained convolutions with propagation along the Laplacian's smooth eigenvectors, gated by a Barontini entropic clock that terminates sampling intrinsically.
Spectral indexing for vector similarity search combining cosine similarity with graph-Laplacian roughness (λτ-indexing) to produce topology-aware similarity scores. Published in the Journal of Open Source Software.
A transformer architecture that reasons through vibrational (oscillatory) modes in embedding spaces, using spectral decomposition to uncover latent structure beyond static attention patterns.
A library for vector analysis, retrieval and curation using graph-wiring techniques. Explores how topological structure in embedding spaces improves retrieval quality beyond naive cosine similarity.
Epiplexity measures spectral feature interactions in high-dimensional embedding spaces, providing a formal framework for understanding how graph Laplacian eigenstructure influences retrieval quality and manifold geometry.
Graph Wiring, epiplexity, and the next generation of tools for machine learning and LLM operations.
A philosophical and personal journey from information technology to AI, tracing the shift from Big Data through Machine Learning to Large Language Models.