Master Thesis GPU-Accelerated Particle Simulation for OpenFOAM at Bosch Group

Renningen, Baden-Württemberg, Germany -

Full Time

Start Date

Immediate

Expiry Date

16 Jun, 26

Salary

0.0

Posted On

18 Mar, 26

Experience

0 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

GPU-Accelerated Simulation, Particle Tracking, OpenFOAM, Python, NVIDIA Warp, CFD, Collision Detection, 3D Geometries, Data Exchange, Benchmarking, Numerical Simulation, Continuum Mechanics, ParaView, Git, HPC Clusters

Industry

Software Development

Description

Company Description At Bosch, we shape the future by inventing high-quality technologies and services that spark enthusiasm and enrich people’s lives. Our promise to our associates is rock-solid: we grow together, we enjoy our work, and we inspire each other. Join in and feel the difference. The Robert Bosch GmbH is looking forward to your application! Job Description In many industrial and research applications, tracking millions of particles within a fluid flow is essential, but current CPU-based methods are too slow. This project offers an exciting opportunity to break that bottleneck by building a state-of-the-art solver that leverages the massive power of modern GPUs to accelerate simulations by orders of magnitude. Join us in developing a cutting-edge tool that integrates directly with the industry-standard Computational Fluid Dynamics (CFD) software OpenFOAM, and make a significant impact on what's possible in computational science. As a part of your Master thesis, you will conduct a literature review on state-of-the-art methods for Lagrangian Particle Tracking, GPU computing in CFD and particle-wall interaction. You will develop a high-performance particle tracking solver using Python and the NVIDIA Warp framework to run on the GPU. In addition, you will implement a method for collision detection with complex 3D geometries and create a pre-processing pipeline to prepare simulation data (e.g., flow fields and meshes) from OpenFOAM for the GPU. Furthermore, you will integrate the new solver into a standard OpenFOAM workflow, establishing a seamless data exchange. Last but not least, you will validate and benchmark your solver's performance against OpenFOAM's native tools, quantifying the massive speedup. Qualifications Education: Master studies in the field of Engineering, Physics or comparable Experience and Knowledge: profound knowledge of and experience in numerical simulation methods, as well as a solid understanding of continuum mechanics; very good programming skills in Python; initial experience with OpenFOAM, NVIDIA Warp and ParaView is desirable; ideally, initial experience with Git and working on HPC clusters Personality and Working Practice: you are able to proactively develop new ideas, find solutions independently and complete tasks efficiently, demonstrating a high degree of self-motivation Work Routine: partially mobile working possible, ideally with 3 - 4 office days per week Languages: business fluent in English and good in German Additional Information Start: according to prior agreement Duration: 6 months Requirement for this thesis is the enrollment at university. Please attach your CV, transcript of records, examination regulations and if indicated a valid work and residence permit. Diversity and inclusion are not just trends for us but are firmly anchored in our corporate culture. Therefore, we welcome all applications, regardless of gender, age, disability, religion, ethnic origin or sexual identity. Need further information about the job? Alexander Fuchs (Functional Department) +49 711 811 93399 Work #LikeABosch starts here: Apply now! #LI-DNI Legal Entity: Robert Bosch GmbH

Responsibilities

The role involves conducting a literature review on particle tracking and GPU computing, followed by developing a high-performance particle tracking solver using Python and the NVIDIA Warp framework for GPU execution. The work also includes implementing collision detection, creating a pre-processing pipeline for OpenFOAM data, integrating the solver, and validating its performance.