Sr. Staff Software Engineer – High Performance GPU Inference Systems
GroqSalary not specified
Full Time
Expert & Leadership (9+ years)
Not SpecifiedCompensation
Senior (5 to 8 years), Expert & Leadership (9+ years)Experience Level
Full TimeJob Type
UnknownVisa
Semiconductor, Consumer ElectronicsIndustries
Requirements
- Masters degree in Electrical, Computer Science, related Science or equivalent combination of education, training and experience
- 3+ years of relevant industry experience
- Strong background in GPU, or SIMD architectures
- Experience specifying Architecture and micro-architectures spec
- Implementing high-level functional and performance models
- Strong communication and collaboration skills, with experience working with cross-functional teams to drive technical solutions
- Deep expertise in GPU Architecture and micro architecture (Special Attribute)
- Experience with GPU APIs, OpenGL, OpenCL, Vulkan (Special Attribute)
- Proficiency in C/C++, SystemC (Special Attribute)
- Proficiency in scripting languages such as Python (Special Attribute)
- Relevant hands-on experience with developing bit accurate architectural functional and performance models (Special Attribute)
- Experience with hardware memory managements units, prefetching or memory subsystems (Special Attribute)
- Experience with Multi-core systems and memory coherency (Special Attribute)
- ML model optimization on GPU Architecture (Special Attribute)
Responsibilities
- Propose innovative GPU Architectural and microarchitectural features to boost PPA (Performance, Power and Area) on various targeted workloads in next generation SOCs
- Identify and deliver GPU subsystem architecture proposals for products in new and existing markets
- Evaluate architecture proposal benefits in collaboration with team of SoC Architects and communicate the results across related engineering audiences (SW, HW, Architecture, Leadership)
- Perform high-level performance modeling/simulation and analysis of GPU features, applications, benchmarks, and complex uses cases
- Deliver architecture/microarchitecture proposals and specifications to the design team and articulate them effectively across audiences ranging from hardware & software engineers to architecture community peers, and to technology leadership
- Collaborate with silicon bring-up and product teams
- Collaborate across teams to bring architecture proposals to fruition across the SOC, Driver, OS, System through detailed documentations
- Analyzing benchmarks, application workloads, and performance simulation results for architecture and microarchitecture optimizations
Skills
GPU Architecture
SoC Architecture
Microarchitecture
Performance Modeling
PPA Optimization
Graphics
Machine Learning
Hardware-Software Co-optimization
Simulation
Bus/Memory Subsystem
Samsung Research America
Develops advanced technology in multiple domains
About Samsung Research America
Samsung Research America specializes in advanced technologies such as next-generation communications, artificial intelligence, digital media, mobile platforms, and digital health. Their innovations include FadeNet, a convolutional neural-network based technology, and the ECG Monitor App, which enables ECG recording using Galaxy Watch for atrial fibrillation screening.
665 Clyde Ave, Mountain View, CA 94043, USAHeadquarters
1988Year Founded
VENTURE_UNKNOWNCompany Stage
HardwareIndustries
501-1,000Employees
Benefits
Onsite Fitness Facility
Subsidized Meals
Coffee Barista Bar
Samsung University
Product Discounts
Dog Friendly Campus
Wellness Programs
Activity Clubs
Related Jobs
RemoteRemoteSenior Solutions Architect, Data Processing
NVIDIASalary not specified
RemoteSolutions Architect, Higher Education and Research
NVIDIASalary not specified
- Full Time
- Senior (5 to 8 years)
RemoteSenior Software Engineer, Next Gen Compute
MotionalSalary not specified
- Full Time
- Senior (5 to 8 years), Expert & Leadership (9+ years)
RemoteGPU Performance tooling engineer
RivosSalary not specified
- Full Time
- Junior (1 to 2 years)
RemoteLead Apparel Designer
MrBeastSalary not specified