AI Compute Architect: Next-Gen Silicon & ML-Driven Design

Acceler8 Talent; Mountain View (CA); Hybrid; USD 180,000 - 300,000; Full time

Job summary

Acceler8 Talent is partnered with a well-funded startup redefining compute for state-of-the-art ML models, seeking a Computer Architect in Mountain View, CA. You will define architectures for next-generation compute engines, translating ML/AI workloads into hardware specs from concept through silicon bring-up.

You'll collaborate with Research, Software, RTL, and Physical Design teams to drive architectural trade-offs, quantify area, power, and timing, and support first-silicon bring-up and

Qualifications

• Strong background in computer architecture and modern compute systems.
• 3+ years experience translating workloads into hardware architectures.
• Ability to evaluate tradeoffs in cost, area, timing and power.
• Knowledge of numeric formats, quantization, and ML precision tradeoffs.

Responsibilities

• Define ISA for compute cores, memory subsystems, and interconnects.
• Derive architectural requirements from ML/AI use cases and model trends.
• Author architectural specifications and interface definitions.
• Specify numeric formats and quantization strategies optimized for AI workloads.
• Estimate area, timing, and power to inform architectural tradeoffs.
• Collaborate with Research, Software, RTL, and Physical Design teams.
• Participate in architecture reviews, design reviews, and test planning.
• Support first-silicon bring-up and post-silicon debug.

Job description

Acceler8 Talent is partnered with a well-funded startup redefining compute for state-of-the-art ML models, seeking a Computer Architect in Mountain View, CA. You will define architectures for next-generation compute engines, translating ML/AI workloads into hardware specs from concept through silicon bring-up.

You'll collaborate with Research, Software, RTL, and Physical Design teams to drive architectural trade-offs, quantify area, power, and timing, and support first-silicon bring-up and