Douw Marx's CV

• Phone: +32 470 51 64 51
• Email: [email protected]
• Location: Leuven, BE
• GitHub: DouwMarx
• LinkedIn: douw-marx-913503163
• Google Scholar: wSgyJ74AAAAJ

Summary

AI safety researcher working on agentic evaluations, risk estimation, and alignment. Contributing to the European Commission Technical Assistance for AI Safety, Redwood Research, AI Futures Project, and METR via Equistamp. Recently completed a PhD at KU Leuven, Belgium, applying machine learning and signal processing to fault detection in rotating machines.

Education

University of Pretoria, Mechanical Engineering (With distinction)

B.Eng

Jan 2015 – Dec 2018

University of Pretoria, Honours and Master's in Mechanical Engineering

M.Eng.

Jan 2019 – Dec 2020

• Machine learning applied to vibration monitoring

• Numerical methods and optimisation

• Control systems and mechatronics

• Particle filters and inverse problems

• Thesis: Towards a hybrid approach for diagnostics and prognostics of planetary gearboxes

KU Leuven, Fault detection in rotating machinery

PhD

Sept 2019 – Oct 2025

Marie Skłodowska-Curie PhD fellow at KU Leuven.

• Thesis: Fault Detection in Rotating Machinery Using Domain Knowledge and Reference Data

• Published 5 peer-reviewed conference papers

• Proposed and led 4 Master's research projects in machine learning and signal processing

• Regularised unsupervised deep learning models

• Differentiable signal processing methods

Experience

Equistamp, Research Engineer

Leuven, Belgium

Aug 2025 – present

1 year

• Contributing to EU AI Office evaluations on CBRN, loss of control, and harmful manipulation

• Contributing to Redwood Research's LinuxArena, a control setting for highly privileged AI agents

• Contributor to Redwood Research's ASMR-Bench, a benchmark for detecting AI sabotage in ML research

• Baselining for Andon Labs, Redwood Research, and METR

• Credited for feedback on AI 2040: Plan A, AI Futures Project

• Evaluation selection for risk modelling and value of information

KU Leuven, Marie Skłodowska-Curie PhD Fellow

Leuven, Belgium

Sept 2021 – Sept 2025

4 years 1 month

Research on fault detection of rotating machines using unsupervised learning and differentiable signal processing methods.

• Published 5 peer-reviewed conference papers

• Proposed and led 4 Master's research projects

• Research secondments at INSA Lyon, France and SafranTech, Paris, France

• Runner-up in PHM 2023 Conference Data Challenge, Salt Lake City, Utah, USA

Wolfram MathCore, SystemModeler Intern

Linköping, Sweden

May 2021 – July 2021

3 months

Develop Virtual labs using Wolfram System Modeler and Mathematica.

XRAM Technologies, Data Analyst and Mechanical Engineer

South Africa

Jan 2021 – Sept 2021

9 months

Build data-driven measurement models for electrode length prediction in electric-arc furnaces.

• Furnace electrode length prediction

• Chemical process data analysis

• Bayesian structural models and Gaussian process regression

Wolfram Summer School, Participant

USA

June 2020 – July 2020

1 month

Towards universal robotics

• Cellular Automata

• Inverse Kinematics

University of Pretoria, Lab Teaching Assistant

Pretoria, South Africa

Jan 2017 – Dec 2020

4 years

• Experimental design

• Machine repair

• CAD and CNC machining

• Design for manufacturing

Publications

Scientific articles

Jan 2025

Patent for a novel parallel kinematic planar mechanism: WO2020208551A1

Feb 2022

Constitutional Sensitivities of Preference Models

Jan 2025

Apart Research Hackathons: AI monitoring at low audit budgets, and Automated risk modelling for evaluation value-of-information estimation

Jan 2026

Workshop: Agentic AI safety

Jan 2026

Talk: Does your LLM care about the same things you do? (75th Data Science Leuven Meetup, slides)

Feb 2026

skills and tools

Programming/Mathematical Modelling

Python (PyTorch, Pandas, SciPy, OpenCV, Dash, LangChain, Scikit-learn), Matlab, C++, Mathematica, Modelica

CLI Tools

HPC with Slurm, Linux, LaTeX, Arduino, Git, Vim, Emacs

Simulation and Computer-aided design

Solidworks, Siemens NX, Ansys, etc.

Languages

Fluent in English and Afrikaans, understands Dutch.

Certificates

EA Introductory Program: Effective Altruism Introductory Program

AI Alignment Course: Bluedot technical alignment course with project: Constitutional sensitivities of preference models.

Fundamentals of Accelerated Data Science: Fundamentals of Accelerated Data Science

Introduction to Deep Learning: Introduction to Deep Learning

Interests

Music

Woodworking

Hiking

Effective altruism