Datacenter AI Network & Compute Architect

Tenstorrent; Santa Clara (CA); Remote; USD 100,000 - 500,000; Full time

Job summary

Tenstorrent is seeking an Interconnect and Compute Architect to help define and build next-generation CPU networking architecture for datacenter and automotive robotics applications. The role emphasizes collaboration across hardware, software, and systems teams to refine networking requirements and drive low-latency, scalable Ethernet fabrics for AI/ML workloads.

The position is remote, based out of North America, with compensation ranging widely to reflect experience and impact.

Qualifications

• Experience with Ethernet network architecture and performance modeling.
• Background in die-to-die interfaces and related protocols.
• Familiarity with on-chip and off-chip Ethernet fabrics.
• Experience with datacenter networking architectures (UALink, NVLink, Broadcom SUE).
• Experience with scale-out RDMA protocols (RoCE, InfiniBand).

Responsibilities

• Contribute to datacenter networking and future robotics/automotive devices.
• Collaborate across hardware, software, and systems teams to define networking requirements.
• Guide architectural decisions at the intersection of forwarding, buffering, modeling, and RTL design.
• Help drive next-generation CPU networking architecture for AI/ML workloads.

Skills

Ethernet networking

Die-to-die interfaces

Datacenter networking

RDMA protocols

Tools

UALink

NVLink

Infiniband

RoCE

Broadcom SUE

Job description

Tenstorrent is seeking an Interconnect and Compute Architect to help define and build next-generation CPU networking architecture for datacenter and automotive robotics applications. The role emphasizes collaboration across hardware, software, and systems teams to refine networking requirements and drive low-latency, scalable Ethernet fabrics for AI/ML workloads.

The position is remote, based out of North America, with compensation ranging widely to reflect experience and impact.