Senior AI Compiler Engineer, MLIR
NVIDIAJob Title
Senior AI Compiler Engineer, MLIR
Role Summary
Join NVIDIA's compiler team to build an MLIR-based AI compiler that powers inference across data center and edge GPUs. The role focuses on compiler representation, optimizations, kernel generation, and performance for modern deep learning workloads.
Experience Level
Senior-level. The posting requests candidates with at least 3+ years of relevant work or research experience; the role expects autonomous engineers who can define and lead projects.
Responsibilities
You will design and implement MLIR-based compiler components and collaborate with framework and hardware teams to deliver high-performance inference.
- Develop MLIR-based graph representations and optimizations for current and future GPU architectures.
- Define APIs and MLIR dialects and implement compiler optimizations and kernel generation for neural networks.
- Conduct performance analysis and tuning to meet targets for runtime, memory use, and build times.
- Partner with framework (e.g., PyTorch/JAX) and hardware teams to enable new model patterns and architectural features.
- Contribute to general software engineering tasks: design, testing, debugging, and code reviews.
Requirements
Must-have technical skills and professional abilities.
- 3+ years of relevant work or research experience in performance analysis and compiler optimizations.
- Experience with compiler technologies such as MLIR, XLA, and LLVM.
- Strong programming and software design skills in C/C++ and Python, including debugging, performance analysis, and testing.
- Ability to work independently: define project goals and scope and lead development efforts.
- Strong interpersonal skills and ability to work effectively on a fast-moving, product-focused team.
Nice-to-have:
- Understanding of deep learning models, algorithms, and frameworks such as PyTorch and JAX.
- Experience with GPU kernel generation focused on high performance and fast builds.
- Proficiency with GPU architecture and CUDA or OpenCL programming.
- Experience mentoring early-career engineers or interns.
Education Requirements
Bachelor's, Master's, or Ph.D. in Computer Science, Computer Engineering, or a related field — or equivalent practical experience.
About the Company
Company: NVIDIA
Headquarters: Santa Clara, California, USA
NVIDIA is a global leader in accelerated computing, renowned for its innovative solutions in AI and digital twins that transform diverse industries. The company specializes in networking technologies, providing end-to-end InfiniBand and Ethernet solutions for servers and storage that optimize performance and scalability. NVIDIA serves sectors such as high-performance computing, enterprise data centers, and cloud computing, constantly reinventing its products and services to stay ahead in the market.
