ML Silicon Performance Lead
Posted Updated
Description
You will drive hardware/software co-design for AI silicon architecture, translating model needs into kernel targets and hardware requirements. You will optimize ML kernels, co-design quantization formats and data structures, define specialized acceleration IP, and lead performance modeling and simulation with compiler and silicon teams.
Responsibilities
- Drive hardware/software co-design across ML research, compiler and silicon teams
- Translate model and workload needs into kernel performance targets and hardware requirements
- Map and optimize ML kernels for the architecture
- Co-design support for new data structures and quantization formats
- Define and help develop specialized acceleration IP
- Drive ML performance modeling and simulation with the compiler team
- Specify and validate new IP with the silicon team
Requirements
- Deep experience with ML accelerator architecture
- Ability to translate model behavior into kernel requirements and hardware decisions
- Experience building or using accelerator performance models and simulators
- Hands-on experience optimizing ML kernels
- Understanding of quantization and numerical formats
- Experience with hardware/software co-design
- May need to meet U.S. export control legal status requirements
Benefits
- Equity
- Performance-related bonus
- Medical, dental and vision insurance with HSA employer contributions
- Health FSA, Dependent Care FSA and commuter pre-tax accounts
- 401(k) with employer match
- Paid parental leave
- Paid medical and caregiver leave
- Flexible PTO
- 13+ paid company holidays
- Mental health and wellness support
- Employer-paid life and disability coverage
- Learning and development stipend
- Daily meals in offices and meal delivery credits
- Relocation support
- Charitable donation matching and wellness stipends
Skills
Sign in to read and join the discussion.