Remote CPU Architect: Vector, Matrix AI Compute

Tenstorrent; Northern (KY); Hybrid; USD 100,000 - 500,000; Full time

Job summary

Tenstorrent in the United States is seeking an experienced CPU Architect/Micro-Architect to lead the design of vector (RVV), floating point, and matrix extensions for high-performance RISC-V compute engines.

You will shape architecture and micro-architecture of compute units and subsystems, collaborate with software teams, silicon designers, and IP partners to optimize performance, power, and area for HPC/AI workloads. This role is remote, based out of North America.

Qualifications

• 5+ years of experience in CPU design for HPC and AI acceleration.
• Experience designing hardware for matrix FP computation, AI accelerators, vector processing, tensor engines, or ML workloads.
• Knowledge of CPU architecture, memory hierarchy, data movement, cache coherency, and CPU-accelerator interactions.
• Experience defining architectural specifications and leading cross-functional teams from concept to silicon.
• Experience with RTL development on cutting-edge AI frontier models.

Responsibilities

• Drive architecture and micro-architecture of compute execution units and subsystems for HPC/AI workloads.
• Translate workload requirements into scalable CPU architectures optimizing performance, power, and area.
• Collaborate with software, silicon designers, and IP partners across hardware and software boundaries.
• Define next-generation compute architectures for open RISC-V CPUs and AI infrastructure.

Skills

CPU architecture

AI acceleration

matrix math

floating point

heterogeneous compute systems

architectural decisions

cross-functional leadership

Job description

Tenstorrent in the United States is seeking an experienced CPU Architect/Micro-Architect to lead the design of vector (RVV), floating point, and matrix extensions for high-performance RISC-V compute engines.

You will shape architecture and micro-architecture of compute units and subsystems, collaborate with software teams, silicon designers, and IP partners to optimize performance, power, and area for HPC/AI workloads. This role is remote, based out of North America.