Job Summary
The role is centered around the leadership of compute architecture for advanced RELIC platforms. This involves establishing the technical strategies related to hardware components such as GPUs, CPUs, and networking fabrics. Additionally, you will be responsible for developing performance and total cost of ownership (TCO) models that facilitate informed decision-making and overseeing the initiation and validation processes for new cluster-scale systems.
Responsibilities
- Define the technical direction for hardware components, including GPUs, CPUs, and networking fabrics.
- Create performance and TCO models to support strategic decision-making.
- Lead the bring-up and validation of cutting-edge cluster-scale systems.
Qualifications
- Minimum of 10 years of experience in systems architecture with a focus on AI, HPC, or hyperscale computing.
- Demonstrated ability to guide platforms from conceptualization to production.
- Extensive knowledge in scale-up and scale-out architectures, GPU technologies, and contemporary inference software stacks.
