PhD Position - Efficient Long-Context Large Models for Vision and Vision-Language-Action Systems (f/m/d)

PhD Position - Efficient Long-Context Large Models for Vision and Vision-Language-Action Systems (f/m/d)

• Institute of Measurement and Control with Machine Laboratory (MRT)
• 3 years
• as soon as possible
• Full-time
• 59,300.00 to 63,600.00 EUR gross per year

Share this job!

For more than one decade the Institute of Measurement and Control Systems (MRT) at KIT has been one of Germany’s leading autonomous driving labs. Its unique advantage is the availability of experimental vehicles with sensors, actuators and a complete software stack for automated urban driving. The existing equipment and experience not only enables continuous cutting-edge research in all areas of autonomous driving, but also a wide range of collaborations with leading industrial partners. Research highlights of the MRT are, among others, the successful participation in autonomous driving competitions as well as the development of highly influential benchmark suites like KITTI and KITScenes.

Your Tasks

Large foundation models and vision-language-action models increasingly rely on long context windows to reason over high-resolution images, videos, multi-camera sensor streams, maps, interaction histories and language instructions. However, standard attention mechanisms scale unfavorably with context length, and large models remain difficult to deploy under real-time, memory and energy constraints in autonomous systems. You will investigate efficient long-context models for computer vision and VLA systems and apply it to autonomous driving.

The research will combine attention optimization, token reduction, model pruning and quantization to make large models scalable while preserving accuracy, robustness, and downstream action quality. The research will build on established ideas from Transformers, long-sequence attention, memory-efficient attention, vision transformers, deep compression, and recent VLA systems.

Your Profile

You are a dedicated and creative person with

• an excellent Master’s degree in engineering, computer science, robotics or similar
• proven knowledge of deep learning and large model architectures
• experience in software development for deep learning
• interest in working independently and scientifically, and
• eagerness to actively participate in a great international team.

We Offer

• Science for Impact : Engage with topics of societal relevance — in an excellent scientific environment that enables change.

• Career‑Building and Developmental Opportunities : We provide you with a structured onboarding program, a broad spectrum of continuing‑education options, and personalised support, thereby fostering your individual growth.

• Flexible Working Hours : Take advantage of flexible‑hours schemes, remote‑work options, and a 30‑day annual leave entitlement to achieve an optimal work‑life balance.

• Family-friendliness : The “KIT‑Family +” program assists you in reconciling work and family life by offering childcare services, holiday activities, a parent‑child office space, and assistance with caring for relatives.

• Stay Healthy : Under the motto “Fit at KIT – Body, Mind and Soul,” we promote your well‑being through fitness classes and mental‑health programmes.

• Individualised Extra Benefits : Enjoy a corporate pension (VBL), a €25 monthly contribution toward a JobTicket BW, plus a broad selection of cultural and recreational programmes.

Job location: Karlsruhe (and Eggenstein-Leopoldshafen) Salary: Salary category 13 TV-L; classification is based on personal and professional qualifications. Contract duration: 3 years

Contact person in line-management Dr. Martin Lauer martin.lauer@kit.edu

If you have general questions about the application process, please contact Julia Boldt Personalservice (PSE) julia.boldt@partner.kit.edu At KIT we value the diversity of our employees; different perspectives and backgrounds enrich our work. We therefore welcome applications from all candidates. Women are especially encouraged to apply. Applications from recognized severely disabled individuals are given preferential consideration when qualifications are equal. Application up to: 2026-11-08 Job posting number: 1252/2026

Apply now!