Liam Chalcroft

Curriculum Vitae

Machine learning researcher working on medical and spectral imaging. My research is on models that generalise beyond their training distribution: domain generalisation, physics-constrained synthetic data, and self-supervised pre-training for 3D imaging. Currently applying that work to spectral imaging as Founding Computer Vision Scientist at Prospectral.

Experience

  • 2025 – present
    Founding Computer Vision Scientist Prospectral, London
    • Lead machine learning research and its integration into the wider product.
    • Build production systems spanning spectral sensing, computer vision and model deployment.
    • Own technical strategy for spectral imaging AI.
  • 2024
    Computer Vision Researcher Tractive, London
    • Led ML research at an a16z-backed pre-seed startup applying 3D generative AI to retopology.
    • Trained transformers at scale with PyTorch and FSDP on Google Cloud.
    • Wrote production backend code in C++ and Rust.
  • 2021 – 2026
    PhD Researcher Wellcome Centre for Human Neuroimaging, University College London
    • Built a physics-constrained synthetic data framework for stroke lesion segmentation that transfers to unseen clinical scanners and sequences.
    • Designed convolutional attention architectures for 3D segmentation, presented at NeurIPS 2023.
    • Developed sequence-invariant contrastive pre-training for 3D MRI encoders.
    • Contributed to the ISLES'22 challenge ensemble published in Nature Communications.
  • 2020 – 2021
    MRes Researcher University College London
    • Built hypernetwork-based segmentation conditioned on imaging domain.
    • Studied image-level false positives in segmentation, published at MICCAI 2021.
  • 2018 – 2019
    Research Scientist, Intern Schlumberger Cambridge Research, Cambridge
    • Characterised non-Newtonian drilling fluids by rheology and diffusing-wave spectroscopy.

Education

  • 2021 – 2026
    PhD, Machine Learning University College London
  • 2020 – 2021
    MRes, Medical Imaging University College London · Distinction
  • 2016 – 2020
    MSci, Chemical Physics University of Bristol · First Class Honours

Teaching and supervision

  • 2023 – 2024
    Fellowship Project Supervisor Fatima Fellowship
  • 2022 – 2026
    MSc Project and Research Supervisor University College London
  • 2022 – 2024
    Tutor, Machine Learning and Data Science Cambridge Spark
  • 2022
    Outreach Project Supervisor In2Research and University College London
  • 2021
    Teaching Assistant and Guest Lecturer COMP0090 Introduction to Deep Learning, University College London

Grants

  • Hardware
    NVIDIA Academic Hardware Grant Estimated value £5,000
  • Cloud
    Google Cloud research credits Estimated value $1,000

Technical

Languages Python, Rust, C++, MATLAB

Frameworks PyTorch, MONAI, SPM

Domains Medical image analysis, domain generalisation, synthetic data, self-supervised learning, generative modelling, spectral imaging