Performance Architect CPU Cluster
Tenstorrent is an AI-computing company that sells AI hardware and licenses AI and RISC-V intellectual property.
Funding history
Investors
About Tenstorrent
Tenstorrent builds computers for AI, including AI processors, scalable server systems, and open-source software and compiler tooling. It also licenses AI and RISC-V IP for customers building customized silicon.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will shape CPU cluster performance and scalability across cores, cache hierarchies, coherent interconnects, memory bandwidth, and system behavior. You will build and use performance models and simulations, analyze workloads and bottlenecks, lead architectural tradeoff studies, and translate performance findings into design decisions.
Requirements
- Understanding of CPU microarchitecture and performance
- Knowledge of cores, caches, interconnects, and memory systems
- Experience with modeling, simulation, and workload analysis
- Ability to analyze cluster-level performance bottlenecks and scaling challenges
- Knowledge of latency, bandwidth, quality of service, utilization, and scalability
Responsibilities
- Analyze and optimize CPU cluster performance, cache hierarchies, interconnects, coherence, and memory access behavior
- Build and use performance models and simulation environments such as Gem5
- Study workloads to identify cache, coherence, bandwidth, latency, contention, and communication bottlenecks
- Lead architectural tradeoff studies across performance, scalability, bandwidth, latency, power, and implementation complexity
- Translate performance analysis into concrete design decisions