About the Role
Title: GPU Architect
Location: Virtual – USA
Job Description:
You’ll be working within the GIA Architecture group (Graphics and AI Architecture) who develops and architects Intel’s next generation shader core. This team drives end to end architecture specifications across graphics and compute IP for highly scalable SOC’s.
Responsibilities include:
Conducts competitive analysis and standards efforts, industry trends, and customer requests to develop hardware and software feature roadmap meeting platform needs.
Ensures interoperability of hardware and software throughout the product life cycle.
Drives GPU functionality, connectivity, configuration, performance, timing, power, and area goals.
Evaluates feasibility tradeoffs and explores and defines new approaches and novel architectures for GPU.
Delivers optimized GPU for multiple segments spanning from ultralow power through client and into high performance GPU, super compute, and customized GPU offerings.
Develops testing approach and preliminary test plans, performs behavioral and/or performance modeling of new features and configurations, and conducts analysis of results using advanced statistics and data predictions for benchmarking and determining ROI of areas for improvement.
Provides experimental/proof of concept changes for proposing design alternatives meeting performance, power, area, and timing constraints.
Reviews, challenges, and influences cross functional roadmaps and defines technology targets for future GPUs.
Collaborates with architects, design engineers, verification engineers, and research teams to improve the overall design of GPU and overcome performance bottlenecks and constraints.
Works hand in hand with presilicon and postsilicon teams to debug, root cause, and identify workarounds and solutions for critical failures.
Qualifications:
Minimum qualifications are required to be initially considered for this position. Preferred qualifications are in addition to the minimum requirements and are considered a plus factor in identifying top candidates.
Minimum Qualifications:
BS/BE, 12+ years of experience
Background in GPU and/or CPU design
Architecture/Microarchitecture experience
Experience in low power design
Expertise in performance analysis and attainment
Preferred Qualifications:
MS/ME, 10+ years of experience
Graphics and 3D programming
Experience in AI/ML algorithms
Experience in ISA (Instruction Set Architecture) definition
Expertise in C++, Python, RTL design
Requirements listed would be obtained through a combination of industry relevant job experience, internship experiences and or schoolwork/classes/research.