About the job
NVIDIA is hiring software engineers for its Deep Learning & AI Compiler (DLC) team. The DLC has been the backbone of NVIDIA’s inference engine, spanning across data centers, personal devices, automotive, and robotics. The compiler must deliver leading inference performance, fast build time, reduced memory footprints, and ease of use in the forms of both Ahead-of-Time and Just-in-Time. Join the team building the DLC which will be used by the entire deep learning community.
Responsibilities
Develop compiler IR, programming model and optimizations for future GPU architectures.
Collaborating with members of the deep learning software framework teams and the hardware architecture teams to accelerate the next generation of deep learning software.
Scope of these efforts includes defining public APIs, performance optimizations and analysis, crafting and implementing compiler optimizations and kernel generation for neural networks, and other general software engineering work.
Qualifications
Minimum
Bachelors, Masters or Ph.D. in Computer Science, Computer Engineering, related field or equivalent experience.
3+ years of relevant work or research experience in performance analysis and compiler optimizations.
Experience with compiler technologies (e.g., MLIR, XLA, and LLVM etc.)
Excellent C/C++ and Python programming and software design skills, including debugging, performance analysis, and test design.
Ability to work independently, define project goals and scope, and lead your own development efforts.
Strong interpersonal skills are required along with the ability to work in a fast moving & dynamic product-oriented team.
Preferred
Understanding of deep learning models, algorithms and frameworks, such as PyTorch, XLA etc.
Understanding of LLM inference optimizations and techniques.
GPU kernel generation with high performance and fast build time.
Proficient in GPU architecture. CUDA or OpenCL programming experience.
Track record on new hardware bring-up is a plus.