PhD: Safe Online Optimization for Distributed Systems

TUE; Eindhoven; On-site; EUR 36,000 - 45,000; Full time

Benefits offered by this job

ABP pension

Leave days 29–41 per year

Commuting allowance

Home internet allowance

OpenUp mental health support

Job summary

TU/e Eindhoven invites applications for a four-year PhD position in the Control Systems group of the Department of Electrical Engineering. You will work on safe Bayesian optimization for time-varying, distributed, safety-critical systems, with experimental validation in drone labs and a smart building project.

This primarily theoretical research focuses on new algorithms, convergence and safety guarantees, using online learning, Gaussian processes and distributed estimation.

Qualifications

• Master's degree in a relevant field (Control Eng., Electrical Eng., Mechanical Eng., or Mathematics).
• MSc in the listed field with expected graduation date if still studying.
• Curiosity-driven, research-oriented attitude.
• Willingness to develop teaching skills and coach students.
• Programming knowledge (Python, Julia).
• Fluent in English (C1).

Responsibilities

• Develop safe Bayesian optimization algorithms for time-varying settings.
• Design distributed learning/optimization schemes with partial information and no central coordination.
• Study time-space decomposition to stay tractable in high dimensions.
• Derive convergence, regret and safety guarantees for large-scale non-stationary environments.
• Use online learning, Gaussian processes, distributed estimation and control theory.
• Turn theory into algorithms validated on UAV tracking/obstacle avoidance and temperature control in a Swiss building.
• Publish in CDC, TAC, NeurIPS, ICML and collaborate with academic partners.

Skills

Python

Julia

Research mindset

English proficiency

Education

Master's degree in Control Eng./Electrical/Mechanical/Math

Tools

Gaussian processes

Job description

TU/e Eindhoven invites applications for a four-year PhD position in the Control Systems group of the Department of Electrical Engineering. You will work on safe Bayesian optimization for time-varying, distributed, safety-critical systems, with experimental validation in drone labs and a smart building project.

This primarily theoretical research focuses on new algorithms, convergence and safety guarantees, using online learning, Gaussian processes and distributed estimation.