Tenstorrent
Interconnect and Compute Architect
$100K–$500K
Santa Clara, California, United States · Full-time · Posted Feb 26, 2026
- Experience
- No specific years stated; candidates at various experience levels are welcome.
- Visa sponsorship
- Employment is contingent on eligibility to access U.S. export-controlled technology; depending on citizenship/permanent residency status, prior license approval may be required. Offers may be rescinded if employment is not possible under U.S. export laws.
About the job
Contribute to next-generation CPU networking architecture for datacenter AI/ML workloads and emerging robotics/automotive devices, spanning architectural decisions, modeling, and RTL design.
What you'll do
- Help define and build datacenter networking architecture and future low-power robotics/automotive devices for AI/ML compute and sensor ingest.
- Guide architectural decisions across forwarding, buffering, modeling, and RTL design.
- Collaborate with hardware, software, and systems teams to define and refine networking requirements.
What they ask for
- Knowledge of Ethernet network architecture and performance modeling.
- Experience with die-to-die interfaces, protocols, and design tradeoffs.
- Understanding of how Ethernet concepts map to on-chip and off-chip fabrics.
- Experience with datacenter scale-up architectures and scale-out RDMA protocols.
Pay
$100k - $500k (total compensation, including base and variable compensation targets)
Tools
Ethernet, UALink, NVLink, Broadcom SUE, RoCE, Infiniband, RTL
AI focus
Architect networking for AI/ML workloads, including datacenter networking and robotics/automotive compute and sensor ingest.
Model-written summary · the original posting is authoritative