Future. Discover. Together.
If you are passionate about start-ups, we are excited to present you with this fantastic opportunity at HHI. Our vision? To accelerate the creation of groundbreaking, technology-driven start-ups. We rely on talents like YOU – with a mix of deep-tech projects, financial support, professional facilities, and a strong network of mentors and coaches. As part of our project with the start-up Kukan, we are looking for a Student Assitant in 3D Reconstruction & AI. In cooperation with the start-up Kukan, we are developing innovative applications that combine 3D Gaussian Splatting, 3D reconstruction, and conversational AI to create photorealistic digital twins. Become part of our team and join us on a journey of research and innovation!
Be part of change
* Testing new deep learning architectures for 3D reconstruction and scene understanding
* Analyzing and preprocessing various data types (3D point clouds, images, depth maps, etc.)
* Reviewing the latest literature on 3D Gaussian Splatting, NeRF, and related technologies
* Orchestrating and documenting deep learning experiments
* Processing and visualizing large-scale 3D datasets
* Applied research in exciting real-world projects
* Preparing presentations
* Testing software and frameworks for 3D reconstruction pipelines
What you contribute
* Enrolled in a master’s program (Berlin/Brandenburg) in computer science, mathematics, statistics, physics, electrical engineering, or a related field
* Strong expertise in computer vision with a focus on modern 3D reconstruction techniques
* Extensive experience with PyTorch: confident training of machine learning models on single- and multi-GPU setups, and ability to work with existing codebases to quickly get training pipelines running
* Deep research interest in one or more of the following areas: 3D Gaussian Splatting, Neural Radiance Fields (NeRF), 3D scene understanding, multimodal learning, self-supervised learning, general computer vision
* Experience in frontend development with Three.js for advanced 3D visualizations (strong plus)
* Knowledge of Rust for high-performance computing applications (advantageous)
* Solid understanding of deep learning fundamentals
* Strong data engineering skills in Python, including proficiency with NumPy, Pandas, SQL, Bash, Docker, git, and other relevant tools
* High willingness to clean and structure large, messy datasets
* Enthusiasm for clean, maintainable, and well-structured code
* Diligent and responsible approach to implementing, verifying, and documenting algorithms
* Excellent proficiency in spoken and written English
* Willingness to work on-site at least 3 days per week at the Fraunhofer HHI Accelerator at Silicon Allee in Berlin
What we offer
* Fascinating challenges in a scientific and entrepreneurial setting
* Attractive salary
* Modern and excellently equipped workspace in central location
* Great and cooperative working atmosphere in an international team
* Flexible working hours
* Opportunities to work from home
The position is initially limited to one year. An extension is explicitly desired.
The monthly working time is 80 hours. This position is also available on a part-time basis. We value and promote the diversity of our employees' skills and therefore welcome all applications – regardless of age, gender, nationality, ethnic and social origin, religion, ideology, disability, sexual orientation and identity. Severely disabled persons are given preference in the event of equal suitability. Our tasks are diverse and adaptable – for applicants with disabilities, we work together to find solutions that best promote their abilities. The same applies if they do not meet all the profile requirements due to a disability.
With its focus on developing key technologies that are vital for the future and enabling the commercial utilization of this work by business and industry, Fraunhofer plays a central role in the innovation process. As a pioneer and catalyst for groundbreaking developments and scientific excellence, Fraunhofer helps shape society now and in the future.
Ready for a change? Then apply now and make a difference! Once we have received your online application, you will receive an automatic confirmation of receipt. We will then get back to you as soon as possible and let you know what happens next.
contact:
Florian Rosendahl
Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute HHI
Requisition Number: 82194 Application Deadline: 12/15/2025