Nikolaus Vertovec

Nikolaus Vertovec

Senior Machine Learning Engineer

Gigaton

Biography

I am a Senior Machine Learning Engineer on the research team at Gigaton, where I develop AI systems for the autonomous optimisation and control of energy-intensive industrial processes. My work draws on machine learning, control theory, and formal methods to improve the efficiency, reliability, and safety of complex physical systems.

My broader research interests lie at the intersection of formal verification, control, and machine learning. I develop methods that provide rigorous guarantees for autonomous and cyber-physical systems, often using only a finite set of observations. My work has focused particularly on neural certificate synthesis, safe reinforcement learning, and physics-informed machine learning. I am especially interested in climate technology, including airborne wind energy and decarbonisation of heavy industry.

Previously, I was a Career Development Fellow in Artificial Intelligence at St Hugh’s College and a member of the Oxford Control & Verification Group in the Department of Computer Science at the University of Oxford. I completed my DPhil at Oxford in 2024, focusing on safety-critical control. Before that, I earned a Bachelor’s degree in Electrical Engineering and Information Technology from ETH Zurich in 2019 and worked at NASA’s Jet Propulsion Laboratory on the Mars 2020 rover mission.

Interests
  • Reachability analysis
  • Statistical learning theory
  • Safe Reinforcement Learning
  • Neural Network Verification
  • Physics-informed neural network
Education
  • DPhil in Engineering Science, 2024

    Oxford University

  • BSc in Electrical Engineering and Information Technology, 2019

    ETH Zürich (Swiss Federal Institute of Technology)

Experience

 
 
 
 
 
St Hugh's College/Department of Computer Science, University of Oxford
Postdoctoral Researcher
Jan 2024 – Present Oxford, UK
Certified learning, and learning for verification with a focus on neural network verification
 
 
 
 
 
Department of Engineering Science, University of Oxford
DPhil
Apr 2020 – Apr 2024 Oxford, UK
Optimal control for safety-critical systems
 
 
 
 
 
NASA Jet Propulsion Laboratory
Intern
Oct 2019 – Mar 2020 Pasadena, USA
Worked on the Mars2020 Rover
 
 
 
 
 
Akademische Raumfahrtsinitiative Schweiz (ARIS)
GNC Engineer
Sep 2018 – Jul 2019 Zurich, Switzerland
Designed the Control Systems for a Sounding Rocket
 
 
 
 
 
ETH Zürich
Teaching Assistant
Feb 2019 – Jul 2019 Zurich, Switzerland
Taught Numerical Methods for second-year bachelor students

Recent Publications

Quickly discover relevant content by filtering publications.
(2025). Scalable Verification of Neural Control Barrier Functions Using Linear Bound Propagation.

PDF

(2025). Certified Neural Approximations of Nonlinear Dynamics.

PDF

(2025). SPoRt -- Safe Policy Ratio. IJCAI.

PDF Cite DOI

(2025). Certified Approximate Reachability (CARe). CDC.

PDF Cite DOI

(2025). Techno-material entanglements and the social organisation of difference. In Ethnic and Racial Studies, 48(9), pp. 1859–1875.

Cite DOI

(2024). Finite sample learning of moving targets . In Automatica, vol. 185, p. 112763.

PDF Cite DOI

(2024). Safety-Aware Hybrid Control of Airborne Wind Energy Systems. In Journal of Guidance, Control, and Dynamics, vol. 47, no. 2, pp. 326–338.

PDF Cite DOI

(2023). State Aggregation for Distributed Value Iteration in Dynamic Programming. In IEEE Control Systems Letters, vol. 7, pp. 2269–2274.

PDF Cite DOI

(2022). Multi-objective low-thrust spacecraft trajectory design using reachability analysis. In European Journal of Control, vol. 69, p. 100758.

PDF Cite DOI

(2022). Verification of safety critical control policies using kernel methods. In 2022 European Control Conference (ECC), London, United Kingdom, pp. 1870-1875.

PDF Cite DOI

(2021). Multi-objective minimum time optimal control for low-thrust trajectory design. In 2021 European Control Conference (ECC), Delft, Netherlands, pp. 1975-1980.

PDF Cite DOI

Contact