Select a track below to explore PhD and visiting researcher opportunities in my group at King's College London, or external collaborations across AI for Science, model evaluation, and space systems.
01 · Research group
How to apply & supervisory style
Initial enquiry. Email your CV and a few sentences on your interests before preparing a formal research proposal.Email CV ↗
Supervisory style. You will be part of a supportive team where everyone explores their own direction. Rather than micromanaging, I give you the space and guidance to make the project your own, and encourage a healthy balance with proper time to rest.
02 · Scholarships & deadlines
PhD studentships (October 2027 entry)
King's NMES Faculty PhD studentship (UK Home students) (October 2027 entry). Sponsored by the Faculty of Natural, Mathematical & Engineering Sciences (NMES) for eligible UK Home students.
King's and China Scholarship Council PhD scholarship (K-CSC) (October 2027 entry · code 2728-KCSC). Full tuition + CSC stipend for Chinese nationals; King's deadline 1 Jan 2027 (supporting docs 15 Jan, CSC 10 to 31 Mar 2027).
King's deadline: 1 January 2027, 23:59 UK time (code 2728-KCSC)Supporting documents: 15 January 2027, 23:59 UK timeNomination outcome: On or shortly after 9 March 2027CSC application: 10 to 31 March 2027
KCL MSci, MSc & summer projects. I occasionally have capacity for KCL MSci, MSc, or summer project students working on simulation based inference, neural emulation, or the Ariel Data Challenge; please email to check current availability.Enquire ↗
Visiting PhD researchers. I welcome visiting doctoral researchers (including CSC Visiting PhD fellows) working on machine learning and exoplanet atmospheres.Enquire ↗
01 · Focus areas
Cross-sector & interdisciplinary collaboration
Collaboration Track
AI for Science & Physics-Informed Emulation
Joint research and knowledge exchange on physics-informed neural surrogates and differentiable forward models for accelerating complex fluid, radiative, and chemical simulations.
Collaborating on domain-grounded ML evaluation benchmarks, out-of-distribution diagnostics, and calibrated uncertainty quantification, building on our experience running the NeurIPS and Kaggle Ariel Data Challenge.
Benchmark designCalibrated uncertaintyOut-of-distribution testingExplainable AI
Research collaboration on machine learning pipelines for spaceborne and remote-sensing instruments, including sensor detrending, non-stationary noise mitigation, and Bayesian retrieval.
Space payload MLSensor calibrationSimulation-based inferenceSpectral retrieval
Invited talks & working groups. I regularly speak at research labs, industry R&D seminars, and policy forums on physics-informed machine learning, uncertainty calibration, and the Ariel Data Challenge.Invite / connect ↗