Selected work across AI engineering, production backends, and physics analysis. The first few are the ones I'd point a recruiter at; the rest follow by most recently updated.

• MemoryHub

  Content-agnostic engine over a markdown memory store with schema-validated writes and an MCP server.
  • Python
  • Pydantic
  • Typer
  • FastMCP
  • LanceDB
  • pytest
  Author (spec-driven, built with AI agents)GitHub ↗

• WeightLifting - transformer from scratch

  Decoder-only char-level transformer (~10.8M params) built and trained from scratch in PyTorch.
  • PyTorch
  • CUDA
  • Weights & Biases
  Sole authorGitHub ↗

• Razor-boost SUSY search (PhD thesis, world's best limits in Run 2 for a period of time)

  Boosted-object Supersymmetry search on 2016 LHC data using razor variables - the analysis behind my PhD thesis, coded, plotted, and statistically analysed in the BoostAnalyzer17 framework.
  • C++
  • Python
  • ROOT
  • WLCG
  Main author of the analysis software for the Razor Boost analysisGitHub ↗

• Single-lepton SUSY search (world-best limits in LHC Run 1)

  Single-lepton Supersymmetry search on 2012 LHC data that set world-best exclusion limits at publication; my personal contribution was measuring the lepton efficiencies.
  • C++
  • ROOT
  • WLCG
  Contributor - lepton efficiency measurementsGitHub ↗

• CMS Pixel Detector offline software & calibration

  Offline reconstruction and calibration software for the CMS Pixel Detector at CERN.
  • C++
  • Python
  • ROOT
  • CMSSW
  • WLCG
  Developer & L3 CoordinatorGitHub ↗

• DataScienceProject - ML fundamentals practice

  Hands-on ML-fundamentals scaffold: logistic regression from scratch, clustering, stats notebooks.
  • Python
  • uv
  • NumPy
  • Jupyter
  Sole author (learning)GitHub ↗

• VideoLearningTool - video knowledge triage

  Desktop app that downloads, transcribes, and LLM-summarises videos for rapid watch/skip decisions.
  • Electron
  • JavaScript
  • Python
  • yt-dlp
  • C#
  • .NET 9
  • SQLite
  • OpenRouter
  Sole author