The company is looking to solve key problems and optimize architecture platforms for cloud and data center environments, particularly in the areas of memory and storage technologies.
Requirements
- In depth knowledge of CPU, memory, storage, and current computer system architectures
- Software development in C/C++, Python with experience in multi-threading programming
- Linux Kernel/Driver/User Space development experience
- Good understanding of Embedded system including knowledge of I/O and HW/SW interface
- Advanced knowledge and development experience with CXL, PCIe/NVMe protocol
- Experiences in hardware acceleration and software stack programming model (OpenCL/CUDA) in AI/MI using GPU/CPU/FPGA system
Responsibilities
- Research Data Center memory and storage requirements, bottlenecks and pain points, and next generation memory and storage controller architecture
- Analyze and develop applications and build prototypes demonstrating application benefits
- Research emerging technology standards and map to optimal implementation
- Take design from concept modeled with software to implement as a solution with applications, software and firmware
- Develop one-of-a-kind innovative prototypes and contribute to feasibility studies and solution development
- Collaborate with other researchers in the team to develop innovative memory/storage solutions for AI/ML workloads
Other
- Bachelors with 5+ years of relevant industry experience, or Masters with 3+ years or PhD +0 years working or researching experiences in memory or storage technologies, data center system or cloud infrastructures
- Must be highly motivated with excellent verbal and written communication skills
- Ability to meet aggressive project deadlines in a team environment
- Ability to work successfully with cross-functional teams, including coordinating across organizational boundaries and geographies
- Onsite at our San Jose office/headquarters 5 days a week