NVIDIA designs graphics processors, computing systems and software for artificial intelligence and graphics applications.
GPU Compiler Intern
Vous développerez l’infrastructure de compilation pour la programmation GPU en Python, notamment avec CUTLASS CuTeDSL. Le poste couvre la conception de DSL et de dialectes MLIR, l’optimisation de kernels GPU ainsi que le profilage et la validation de leurs performances. Il s’adresse à une personne qui poursuit ou détient un diplôme en informatique ou dans une discipline technique connexe, avec des compétences en Python, C++ et programmation GPU.
- Level : Internship / apprenticeship
- Schedule : Full-time
-
Python
-
C++
- CUTLASS CuTeDSL
- MLIR
- CUDA
- Triton
- LLVM
Information about NVIDIA
- Official domain
- nvidia.com
- Open jobs
- 100
Job details
The full description published by NVIDIA.
Description de l’offre
As GPU Compiler Intern, you will develop compiler infrastructure for Python-based GPU programming, including CUTLASS CuTeDSL. You will work on DSL design, MLIR IR design, and compiler optimizations that translate expressive Python programs into high-performance NVIDIA GPU kernels.
What you will be doing
- Design and implement Python DSL features for GPU kernel authoring, including metaprogramming and IR generation.
- Develop MLIR dialects, transformation passes, and lowering pipelines that preserve the information needed for effective GPU optimization.
- Design and optimize GPU kernels, exploring how IR design and compiler transformations affect generated code and performance.
- Profile, benchmark, and validate compiler and kernel improvements across representative workloads. What we need to see:
- Currently pursuing or holding a Bachelor’s, Master’s, or Ph.D. degree in Computer Science, Computer Engineering, or a related technical discipline, or equivalent practical experience.
- Proficiency in Python and C++, with strong debugging and software development skills.
- Understanding of how Python DSLs work, including metaprogramming, staged execution, and translation into compiler IR.
- Experience with MLIR, including IR construction, transformation passes, or lowering.
- Practical experience with GPU programming, preferably CUDA, and knowledge of GPU execution and memory models.
- Familiarity with performance analysis and optimization, including profiling, memory access patterns, and parallel execution.
- Experience with CUTLASS, CuTeDSL, Triton, LLVM, or other GPU compiler and kernel development tools is a plus.
Requirements
- Bachelor’s, Master’s, or Ph.D. degree in Computer Science, Computer Engineering, or a related technical discipline, or e
- Python
- C++
- Understanding of Python DSLs, metaprogramming, staged execution, and translation into compiler IR
- Experience with MLIR
- Practical experience with GPU programming, preferably CUDA
- Familiarity with performance analysis and optimization
- Experience with CUTLASS, CuTeDSL, Triton, LLVM, or other GPU compiler and kernel development tools
Apply for this job
How do I apply?
The job is published on NVIDIA’s website. Open the original posting ↗ to submit your application. Screeningpass does not fill in a form for you.
Who should you write to at NVIDIA about this role?
Start a contact search from this page. Screeningpass suggests up to three people connected to the role. Choose whom to write to, then Screeningpass looks for their professional email and prepares a message. You review it and send it yourself with Gmail. An email address is not always available, and a reply is never guaranteed.
How much does finding a contact cost?
A search costs 1 credit. Your credit is returned if the search fails. Signing up gives you 3 credits, enough for 3 searches.
What does Screeningpass do?
Screeningpass brings together internships, apprenticeships and jobs published by companies. For a job, Screeningpass finds someone to contact at the company, looks for their professional email and prepares a message using your CV. See how it works in detail.
More jobs at NVIDIA
99 other jobs currently available.
The role develops NVIDIA’s commercial partnerships with independent software vendors and cloud partners across EMEA. It aims to integrate NVIDIA software and frameworks into partner offerings and accelerate their adoption by businesses. The role coordinates sales, technical and product teams and tracks the pipeline and adoption results.
NVIDIA is seeking a Technical Account Manager specializing in HPC and cloud to support its enterprise customers. The role involves resolving technical issues related to the installation, operation, and maintenance of data center technologies, particularly in AI and HPC. The person will work with engineering, marketing, and support teams and help document resolution methods.
NVIDIA is looking for a Senior Account Manager to develop its AI and accelerated computing solutions among capital markets organisations in EMEA. The role involves managing strategic accounts, increasing adoption of NVIDIA platforms and driving revenue growth. It requires 12 years or more of experience selling solutions to decision-makers and a Bachelor’s degree.
- Level : Senior
- Schedule : Full-time
- Education : Five years of higher education
-
Python
-
PyTorch
-
Kubernetes
NVIDIA is looking for a Solution Architect specialising in sovereign AI to support public-sector clients in the UK and Europe. The role involves designing and deploying AI solutions, supporting proofs of concept and advising clients’ and partners’ technical teams. At least five years’ experience is required, along with proficiency in Python, PyTorch, Kubernetes and containers.
NVIDIA is seeking a software engineering intern to join its physics simulation team in Zurich and contribute to developing Newton features and workflows for robot learning. The six-month internship, scheduled for 2027, focuses on numerical simulation, robotics, experiments and software development using tools such as PhysX, MuJoCo, Isaac Sim, Isaac Lab, Warp and CUDA.
NVIDIA is recruiting a deep learning compiler engineering intern to work on CUDA Tile IR in Zurich, Switzerland. The internship focuses on optimising CUDA Tile IR, analysing deep learning networks and developing compiler optimisation algorithms, using C/C++ and technologies such as MLIR, LLVM and XLA.