Intel GPGPU - Machine Learning Architect in Folsom, California

Job Description

Gen Compute Arch GCA team in the Visual and Parallel Computing Group VPG is looking for passionate and driven individuals to help define and build the next generation of highly efficient GPU architectures for Intel. The roles in GCA team include but not limited to understanding the new merging workloads for GPGPU such as Machine Learning, Deep Learning, Computer Vision, AR/VR and High Performance Computing HPC, doing performance and power modelling, workload analysis and performance debug to identify bottlenecks and drive resolution through hardware and/or software fixes. In addition, we develop highly optimized GPU kernels and work with our partner software and enabling teams to help deliver high performant solutions on our GPUs for such workloads. We also work closely with Research Labs/Academia to assess new research/algorithms in these domains and drive the most relevant innovations/features into our architecture to be competitive on such workloads. Ensures platform and its components have the best performance and power balance specifically focusing on graphics hardware components. Research and development of next generation platform designs to continually improve the performance. Conducts system analysis on proprietary and competition platforms, develops advanced hardware tuning and overclocking.


MS or PhD in CS, EE or Mathematics with 10+ years' experience in GPU/CPU Architecture. Knowledge and experience in OpenCL/CUDA/Metal and other such parallel programming APIs required. Knowledge of Deep Learning Algorithms/Networks and Frameworks such as TensorFlow, Caffe and programming languages like python highly desired. Experience in uarch/RTL/Design/process technologies a big plus. Experience in building analytical and/or simulation based performance models and/or in Performance Analysis/Perf Debug also a plus. Excellent written and verbal communication skills required. Should have an aptitude to learn new things quickly in this fast changing domain and flexibility to work on any mix of the above roles as needed.

Inside this Business Group

The Platform Engineering Group (PEG) is responsible for the design, development, and production of system-on-a-chip (SoC) products that go into Intel’s next generation client and mobile platforms. PEG strives to lead the industry moving forward through product innovation and world class engineering.

Other Locations

US, California, Santa Clara

Posting Statement. Intel prohibits discrimination based on race, color, religion, gender, national origin, age, disability, veteran status, marital status, pregnancy, gender expression or identity, sexual orientation or any other legally protected status.