CV

Education

DPhil Statistics, University of Oxford, 2021-26
- PhD student in the Oxford Protein Informatics Group (supervised by Dr. Matthew Raybould, Prof. Yee Whye Teh, and Prof. Charlotte Deane)
- Thesis: Machine-learning and structural modelling of T-cell receptors and TCR:pMHC interfaces
MEng Bioengineeering (1st Class Honours), Imperial College London, 2015-19
Abitur & Int’l Baccaleaureate, German School London, 2009-15

Research Experience

Postdoctoral researcher funded by OpenBind, University of Oxford, Jan. ‘26-present,
DPhil candidate in Statistics, University of Oxford, 2021-2026
Post-graduate research post at the University of Stuttgart, 2020-21.
Masters in Engineering Imperial College London, 2015-2019

Professional experience

Quantitative ML Researcher Internship, G-Research, Jun.’25-Sep.’25
Quantitative ML Researcher Internship, OxFORD Asset Management, Sep.’24-Jan.’25
Postgraduate Research Assistant Uni. of Stuttgart & Max Planck Intelligent Systems, Jun ‘20-Jun ‘21
Machine Learning Engineer, Gestalt Robotics, Nov ’19-Apr ’20
Intern at Venture Capital Fund InHealth Ventures, Sep.-Oct. 2018
Intern at Medical Device Startup Pathfinder Ltd. (previously Stent Tek Ltd.), Jul-Sep ’18
Intern at Engineering Consultancy Cambridge Design Partnership, Jun.-Sep. 2017

Skills

Languages
- English
- German
- conversational French.
Keywords
- Data science, deep learning, machine learning, computational bioinformatics, immunology, protein structures, paper writing, science communication, unit testing, T-cell receptors, finance
Programming
- Python, pytorch, tensorboard, biopython, unittest, flask, ReactJS, C

Publications

Converting diffusions to flows accelerates sampling and suggests over-conditioning of co-folding models on sequence

Quast et.al. (2026). "Converting diffusions to flows accelerates sampling and suggests over-conditioning of co-folding models on sequence." Learning Meaningful representations of Life @ 14th International Conference on Learning Representations. 1(1).

Lymphodepleting chemotherapy potentiates neoantigen-directed T cell therapy by enhancing antigen presentation

Sagie et.al. (2025). "Lymphodepleting chemotherapy potentiates neoantigen-directed T cell therapy by enhancing antigen presentation." Cell Reports Medicine. 6(12).

HeavyBuilder: Analysis of High-Throughput of Antibody Heavy Chain Repertoires in the Structural Space

Gervasio et.al. (2025). "HeavyBuilder: Analysis of High-Throughput of Antibody Heavy Chain Repertoires in the Structural Space." Journal of Molecular Biology. 6(12).

STCRpy: a software suite for T cell receptor structure parsing, interaction profiling and machine learning dataset preparation

Quast et.al. (2025). "STCRpy: a software suite for T cell receptor structure parsing, interaction profiling and machine learning dataset preparation." Bioinformatics. 41(10).

T-cell receptor structures and predictive models reveal comparable alpha and beta chain structural diversity despite differing genetic complexity

Quast et. al., (2009). "T-cell receptor structures and predictive models reveal comparable alpha and beta chain structural diversity despite differing genetic complexity." Communications Biology. 8(1).

Estimating protein flexibility via uncertainty quantification of structure prediction models

Quast & Sweeney et. al., (2024). "Estimating protein flexibility via uncertainty quantification of structure prediction models." Machine Learning for Structural Biology @ NeurIPS 2024. 1(1).

The Observed T cell receptor Space database enables paired-chain repertoire mining, coherence analysis and language modeling

Raybould & Greenshields-Watson et. al. (2024). "The Observed T cell receptor Space database enables paired-chain repertoire mining, coherence analysis and language modeling." Cell Reports. 43(9).