Intern Computer Vision and Sensor Fusion (f/m/x)
At a glance
Junior AI Research role at BMW Group. Munich.
Pay not stated AI Research salary
aimlroles summary, based on the employer's posting.
What you'll do
- Help create 3D scene reconstructions and new viewpoints using data from vehicle sensor setups
- Bring camera, LiDAR, radar and ultrasonic data together to form precise digital copies of driving environments
- Assist scientists and engineers with real autonomous-driving data issues and move reconstructed assets into simulation
- Develop and check a pipeline linking range readings with image-based data for digital twins
- Contribute, if the opportunity arises, to a computer vision or robotics conference paper
What you bring
- You are working toward a master's or Ph.D. in a quantitative discipline such as computer science, robotics or electrical engineering
- You bring theory and hands-on experience in 3D reconstruction, novel view synthesis and methods such as Gaussian Splatting or NeRFs
- You can work confidently in Python and PyTorch, with 3D learning library and GPU computing experience
- You know agentic development workflows, including automated experiments or LLM-supported coding and research agents
Who this fits
This full-time internship suits a master's or Ph.D. student focused on 3D computer vision and sensor fusion. The role is in Munich and lasts four months, with a start date of November second, twenty twenty-six. Good English is expected; German is a plus.
From the employer
THE BEST INTERNSHIP IN THEORY - AND IN PRACTICE.
SHARE YOUR PASSION.
World-leading technologies don’t make it into a BMW until they’ve undergone one of the most challenging journeys imaginable. It takes dynamic teams with outstanding technical skills to take them from the drawing board to the road. That’s why our experts will treat you as part of the team from day one, encourage you to bring your own ideas to the table – and give you the opportunity to really show what you can do.
Our team at the BMW Group explores the intersection of computer vision, sensor fusion, and generative simulation. We focus on multi-modal 3D scene reconstruction and novel view synthesis to build high-fidelity digital twins of real-world driving environments for state-of-the-art simulation platforms.
What awaits you?
- You support multi-modal 3D scene reconstruction and novel view synthesis by leveraging multi-sensor setups in modern vehicles (e.g., surround cameras, LiDAR, radar, and ultrasonic sensors).
- Furthermore, you help fuse these complementary modalities to build metric-accurate, high-fidelity digital twins of complex real-world driving environments.
- In addition, you support experienced scientists and engineers in tackling real-world autonomous driving data challenges and integrating reconstructed assets into simulation platforms.
- Moreover, you help develop and validate a reconstruction and synthesis pipeline bridging sparse and dense range measurements with photometric data for digital twins.
- Furthermore, you may contribute to a top-tier computer vision or robotics conference publication (e.g., CVPR, ICCV, ECCV, NeurIPS, or CoRL).
What should you bring along?
- Studies in Computer Science, Robotics, Electrical Engineering, Applied Mathematics, or a related quantitative field, pursuing a Master's or Ph.D. degree.
- Solid theoretical and practical experience with classical and neural 3D reconstruction, novel view synthesis, and representations like Gaussian Splatting, NeRFs, point clouds, and meshes.
- Strong proficiency in Python and PyTorch, including experience with 3D deep learning libraries (e.g., PyTorch3D, Kaolin, Open3D) and GPU-accelerated computing.
- Familiarity with modern agentic development toolchains and orchestration workflows, such as automated experimentation pipelines and LLM-assisted code and research agents.
- Prior experience with multi-modal sensor fusion, such as camera-LiDAR calibration, radar or ultrasonic point-cloud processing, or sensor dropout robustness is a plus.
- Broad overview of automotive simulation, synthetic data generation, and generative world models, plus a track record of open-source contributions to 3D vision projects.
- Good English skills; German language skills are a plus.
Are you passionate about pushing the boundaries of 3D computer vision and sensor fusion for automotive digital twins? Then Apply now!
What do we offer?
- Comprehensive mentoring & onboarding.
- Personal & professional development.
- Flexible working hours.
- Mobile work.
- Attractive & fair compensation.
- Apartments for students (subject to availability & only at the Munich location).
- And much more, see bmw.jobs/waswirbieten
Start date: Earliest start date 02.11.2026
Duration: 4 months
Working hours: Full-time
You can find helpful tips on your application and the application process here.
At the BMW Group, we place great importance on equal treatment and equal opportunities. Our recruiting decisions are based on the personality, experience, and skills of the applicants. Learn more here.