The AGI Computing Lab is dedicated to solving the complex system-level challenges posed by the growing demands of future AI/ML workloads. Our team is committed to designing and developing scalable platforms that can effectively handle the computational and memory requirements of these workloads while minimizing energy consumption and maximizing performance.
Requirements
- Prior experience simulating/emulating custom/mixed precision AI accelerator arithmetic operations.
- Prior hardware/software co-verification/validation experience and ability to collaborate with both the hardware and the software teams effectively.
- Hands-on experience and skill in deploying new deep learning models on heterogeneous hardware backends.
- Prior experience in the design, development, and optimization of algorithms and acceleration kernels on FPGAs for application offload/acceleration.
- Prior experience in performance profiling and bottleneck analysis is a plus.
Responsibilities
- Design and develop comprehensive hardware/software co-verification/validation tools and infrastructure for emerging memory-centric AI acceleration products/solutions.
- Work with other hardware/software architects to invent new/refine existing custom-precision algorithms for future products, and contribute to feasibility studies.
- Create key IPs, craft and present value-driven business cases, write or publish peer-reviewed papers and/or new product/technology whitepapers.
- Collaborate with universities and international teams.
Other
- BS in Computer/Electrical Engineering or Computer Science with 5+ years of working experiences in silicon development or MS in Computer/Electrical Engineering or Computer Science with 3+ years of relevant working experience or PhD and 0+ years of relevant working experience preferred.
- Must be highly motivated with excellent verbal and written communication skills, and ability to thrive in a collaborative, multi-disciplinary environment.