Ian Buck is vice president of hyperscale and high-performance computing at NVIDIA, where, as head of product for hyperscale AI, Buck manages NVIDIA's AI hardware and software products. NVIDIA's author page describes Buck as the inventor of CUDA and says Buck joined NVIDIA in 2004 after completing a PhD in computer science at Stanford University, where Buck was development lead for Brook, the forerunner to generalized computing on GPUs. Buck is the first author of the 2004 paper Brook for GPUs, which presents a compiler and runtime for general-purpose computation on programmable graphics hardware.1234
At a glance
- Current role
- Vice President of Hyperscale and High-Performance Computing
- Company
- NVIDIA
- Sector
- Company
- Education
- Stanford
- Work listed
- 2
- Sources cited
- 4
- Profile reviewed
Career
At Stanford University, Buck was the development lead for Brook, a compiler and runtime for the Brook stream programming language on graphics hardware, released as a beta source package. Buck was first author of "Brook for GPUs: Stream Computing on Graphics Hardware," a SIGGRAPH 2004 paper, which used the GPU as a streaming coprocessor for general-purpose programs.431
Buck joined NVIDIA in 2004 after completing the PhD, and NVIDIA describes Buck as the inventor of CUDA, its platform for GPU computing. Buck is now NVIDIA's vice president of hyperscale and high-performance computing and, as head of product for hyperscale AI, manages NVIDIA's AI hardware and software products developed with large cloud and AI companies.1
Writing
Buck's posts on the NVIDIA blog cover deployments of NVIDIA systems with cloud providers, including GB200 NVL72 systems at CoreWeave and Oracle Cloud Infrastructure in 2025 and a GB300 NVL72 supercomputing cluster on Microsoft Azure. Later posts describe NVIDIA's collaborations with Microsoft, AWS and Google Cloud and, in July 2026, the NVIDIA Vera CPU, which NVIDIA positions for agentic AI workloads.12
Work and contributions
CUDA
NVIDIA's author page describes Buck as the inventor of CUDA and says Buck helped kickstart the use of graphics processors for general-purpose computing.1
Brook for GPUs (BrookGPU) Published research
First author of "Brook for GPUs: Stream Computing on Graphics Hardware" (SIGGRAPH 2004), which extends C with data-parallel constructs and presents a compiler and runtime that use the GPU as a streaming coprocessor; NVIDIA's page says Buck was the development lead for Brook at Stanford.341
Timeline
- First-authored "Brook for GPUs," a paper for SIGGRAPH 2004.3
- Joined NVIDIA after completing a PhD in computer science at Stanford University.1
- Wrote about Oracle Cloud Infrastructure deploying NVIDIA GB200 NVL72 racks for agentic AI.1
- Wrote about Microsoft Azure's NVIDIA GB300 NVL72 supercomputing cluster built for OpenAI.1
- Wrote about the expanded NVIDIA and AWS partnership announced at AWS re:Invent.1
- Wrote about AI developers adopting the NVIDIA Vera CPU for agentic AI.2
Other documented roles
Roles the sources document that are not confirmed as current.
- PhD student in computer science; development lead for Brook, Stanford University14
Where they work
- NVIDIA 43 people in the wiki
Related people
- Tianqi ChenAlso at NVIDIA
- Song HanAlso at NVIDIA
- Jeff BolzAlso at NVIDIA
- Natalia GimelsheinAlso at NVIDIA
- Bill DallyAlso at NVIDIA
- Gavin UbertiChips and hardware · Inference and serving
- Johannes GäßlerInference and serving · Chips and hardware
- Jeff JohnsonChips and hardware · Inference and serving
- Mitesh AgrawalChips and hardware · Inference and serving
- Awni HannunML frameworks and libraries · Inference and serving
Suggest a correction or removal
Profiles cover public professional work only, and each statement cites a source. If something is out of date, missing or wrong, tell us and link a source. People can also ask for their profile to be corrected or removed.
References
4 sources · profile reviewed Oct 21, 2026 · data updated Oct 21, 2026