PhD: Foundation Models for Automotive Radar Perception

Delft University of Technology (TU Delft); Delft; On-site; EUR 36,000 - 45,000; Full time

Benefits offered by this job

Customisable compensation package

Discounts on health insurance

Monthly work costs contribution

Flexible work schedules

Relocation assistance

Dual Career Programme

Job summary

Delft University of Technology invites applications for a PhD project in automotive radar foundation models. You will work within the Intelligent Vehicles group (Cognitive Robotics) and collaborate with Perciv.AI and NXP Semiconductors to learn general radar representations from unlabeled data and adapt them to various perception tasks.

The PhD spans four years with two contracts, including generous holiday allowance, a performance-based progression, and access to TU Delft's AI resources.

Qualifications

• MSc degree in Computer Science, Artificial Intelligence, Robotics, Electrical Engineering, or a closely related field.
• Strong academic record with solid background in machine learning and deep learning.
• Ability to develop, understand, and critically evaluate ML software, preferably in Python/PyTorch.
• Interest in foundation models, self-supervised learning, multimodal learning, and 3D perception.
• Affinity for translating methodological research into experiments with real automotive sensor data.
• Ability to work independently and in a team.
• Good written and spoken English.
• Experience with radar, signal processing, CV, autonomous driving, or sensor fusion is advantageous.

Responsibilities

• Investigate foundation models for automotive radar and learn general representations across radar configurations.
• Develop and evaluate ML research software on real automotive sensor data and vehicles.
• Collaborate with TU Delft groups, Perciv.AI, and NXP Semiconductors; publish results in top venues.
• Contribute to bridging academic research with experimental demonstrations and datasets.

Skills

Python

PyTorch

ML research

Foundation models

Radar

English (written)

Education

MSc in Computer Science/AI/Robotics/EE

Tools

Job description

Delft University of Technology invites applications for a PhD project in automotive radar foundation models. You will work within the Intelligent Vehicles group (Cognitive Robotics) and collaborate with Perciv.AI and NXP Semiconductors to learn general radar representations from unlabeled data and adapt them to various perception tasks.

The PhD spans four years with two contracts, including generous holiday allowance, a performance-based progression, and access to TU Delft's AI resources.