Compute Server Platform Architect

Responsibilities

• Own the architecture for all server roles in Cerebras clusters, including server types, configurations, and lifecycle strategy.
• Define and maintain server formulas, including counts and ratios per CS-3 count, cluster size, and workload type, with capacity planning and headroom policy.
• Specify platform configurations covering CPU SKU and core strategy, AMD, Intel, and ARM vendor roadmaps, memory topology, PCIe topology and lane budgeting, NIC selection and placement, and local NVMe policy.
• Translate software and runtime flows into measurable hardware requirements, including CPU utilization, memory bandwidth and latency, bursty I/O patterns, queueing, and concurrency limits.
• Develop performance and scaling models; validate them with microbenchmarks and workload-level experiments; identify bottlenecks and drive cross-stack fixes.
• Define the OS, BIOS, firmware, and driver baseline for each server type.
• Evaluate emerging server technologies, including new CPU generations, memory technologies, CXL, NVMe, and SmartNIC/DPU capabilities, through proof-of-concept evaluations.
• Lead technical vendor engagements with OEMs, ODMs, and component vendors to influence roadmaps, request platform controls, and resolve performance or reliability issues.
• Define qualification and acceptance criteria for performance, stability, and operability, and partner with the Infrastructure Hardware TPM on qualification plans and production adoption.
• Support bring-up and deployment debugging in lab and staging environments; drive root-cause analysis for regressions spanning firmware, drivers, the OS, and runtime behavior.

Requirements

• PhD in Computer Science or Electrical/Computer Engineering and 8+ years of industry experience, or a master's or bachelor's degree in Computer Science or Electrical Engineering and 10+ years of industry experience.
• 5+ years of experience in server platform architecture, systems performance engineering, or large-scale infrastructure design for AI/ML, HPC, or performance-sensitive distributed systems.
• Deep understanding of x86 server architecture, including CPU microarchitecture, cache hierarchies, NUMA, memory controllers and channels, and memory bandwidth versus latency tradeoffs.
• Strong Linux systems knowledge, including profiling and performance analysis, scheduling and syscall overheads, memory management behavior, and practical tuning methodology.
• Experience with high-performance I/O paths, including NIC behavior, RDMA/RoCE concepts, and NVMe performance characteristics.
• Ability to create capacity and performance models and validate them empirically with rigorous benchmarking plans.
• Experience working directly with vendors and partners to evaluate platforms, resolve issues, and influence roadmaps.
• Strong cross-functional communication skills and ability to drive technical decisions through tradeoff documents and reviews.
• Familiarity with application and systems software, including C, C++, and Python.

Benefits

• Opportunity to build a breakthrough AI platform beyond the constraints of GPUs.
• Ability to publish and open source cutting-edge AI research.
• Work on one of the fastest AI supercomputers in the world.
• Startup vitality with job stability.
• Non-corporate work culture that respects individual beliefs.
• Continuous learning, growth, and support.