Scientific Machine Learning Engineering Intern

Scientific Machine Learning Engineering Intern About Corintis Corintis offers innovative microfluidic cooling technologies for data centers. Our solutions improve compute sustainability and tackle the excessive electricity consumption associated with data center cooling, which consumes more electricity than New York and London combined. By integrating cooling directly inside the chip, we pave the way for the next generation of AI workloads, supporting applications like generative AI systems, climate modeling, and drug discovery to enable the future of sustainable computing. Working at Corintis Corintis offers a friendly and team-oriented workplace bringing together a diverse group of nationalities to solve the biggest computing challenges of tomorrow. Based on the EPFL campus near Lausanne, we are closely connected to the local ecosystem and are located a few minutes walk from Lake Geneva. Job Description As a Scientific Machine Learning Engineering Intern at Corintis, you'll play a crucial role by leveraging your skills in Scientific Machine Learning (ML) and Computational Science & Engineering to accelerate the optimization of our groundbreaking microfluidic cooling technology. This role offers an exciting opportunity to directly contribute to the evolution of sustainable computing solutions, including, but not limited to, future AI workloads. Responsibilities Apply ML methods such as Neural Operators for Partial Differential Equations (PDEs) to predict the performance of microfluidics for microchip cooling. Enhance current ML models and algorithms for improved prediction accuracy and computational efficiency. Collaborate with a cross-functional team of engineers and scientists to integrate ML solutions into our Computational Fluid Dynamics (CFD) framework and our design and optimization process. Continuously monitor and incorporate the latest research and developments in the fields of ML, CFD and topology optimization into our methodologies. Analyze complex datasets, interpret patterns and trends, and contribute to the evolution of our topology optimization strategies. Contribute to the formulation of objective functions based on specific design criteria and constraints. Develop creative and innovative solutions that address the complex challenges of integrating ML, fluid dynamics and microfluidics. Requirements Background in computational engineering, computational science, mathematics, physics, or mechanical engineering. Extensive knowledge of Machine / Deep Learning techniques and architectures. Proficient in Python and an ML open source library, preferably PyTorch. Experience in working with open source tools and Git (GitHub). Interest in CFD and experience with simulation methods. Ability to think outside of the box and freely discuss creative solutions. Demonstrated ability to write clear, high-quality technical documentation. Autonomous and proactive working style with excellent organization and work ethics. Effective communication skills and the ability to work in a team with diverse professions and cultural backgrounds. Please attach a letter of motivation with your CV Strongly desirable Experience with training large datasets using GPUs, preferably multi-thread training on High Performance Computing (HPC) Systems. Familiarity with using Partial Differential Equations (PDEs) for modeling physical phenomena. Familiarity with the Finite Element Method (FEM) for the numerical solution of PDEs. Experience in reduced-order modeling for the numerical solution of PDEs and / or scientific ML. Experience in applying the aforementioned techniques for fluid dynamics problems (Navier-Stokes and / or Darcy flow). What we offer A dynamic, flexible, innovative, and multicultural work environment. Activity rate : 100% Location : On-site, Corintis SA (Building C), EPFL Innovation Park, Switzerland. Seniority level : Internship Employment type : Internship Job function : Information Technology Industries : Computers and Electronics Manufacturing #J-18808-Ljbffr