Performance Modeling Architect - AI Memory Systems

Job Description

Job Description

Performance Modeling Architect - AI Memory Systems

Job Title: Performance Modeling Architect - AI Memory Systems
Job Location: Santa Clara, CA, or Boston, MA
Compensation: $200K - $250K base DOE plus 25% bonus and meaningful equity
Requirements: AI Memory Systems, Performance Modeling, Memory Expansion (NICs, SmartNICs, CXL, IPU/DPU, NoC), Memory Systems Architecture, ML Systems, CUDA Memory Management

Position Overview
We are seeking a Member of Technical Staff, Performance Modeling to develop performance models for our fabric-attached memory expansion device for AI accelerators. You'll work closely with silicon architects and workload teams to explore design tradeoffs, validate performance assumptions, and identify bottlenecks early in the development cycle. This role is well-suited for engineers who enjoy reasoning from first principles, working with incomplete information, and co-exploring the design space as hardware and software evolve together.

Key Responsibilities

• Build and maintain system-level performance models for a high-bandwidth data movement device operating in the scale-up domain.

• Model workload from software memory access patterns to data distribution in the network and all the way down to on-device memory channels.

• Work day-to-day with silicon architects, system designers, and workload owners to align performance expectations and constraints.

• Identify performance bottlenecks, scaling limits, and sensitivity points across compute, memory, and interconnects in end-to-end workload settings.

• Clearly communicate modeling assumptions, limitations, and conclusions to both technical and non-specialist stakeholders.

Qualifications

• Bachelor's or Master's degree in Electrical Engineering, Computer Engineering, or a closely related field.

• Ability to quickly learn new ML architectures as soon as they come out, and build performance models for them.

• 5-10+ years of experience in performance modeling for data movement devices: NICs, memory expansion cards (e.g., CXL), IPU/DPU, NoC.

• Ability to reason across multiple abstraction layers, from architectural details to system-level performance behavior.

Preferred Qualifications

• PhD in Computer Science, Electrical Engineering, or a related field.

• Prior experience modeling performance for networking protocols with memory semantics.

• Understanding of ML systems: workload sharding, KV caching hierarchies, attention optimizations, trade-offs when deploying ML models at scale, and various assumptions.

• Familiarity with shared memory systems and frameworks (e.g., CUDA VMM).

• Experience with scale-up and high-bandwidth interconnects (e.g., NVLink or similar technologies).

Benefits

• Competitive salary commensurate with experience including base salary, performance-based bonus, and early-stage equity grant
• Comprehensive benefits including health, dental, vision, and life insurance
• Well-equipped, sunny offices in Santa Clara, CA and Boston, MA
• Relocation assistance and visa sponsorship
• Perks include a daily lunch stipend, 401k match, and more
• A collaborative, continuous-learning work environment with smart, dedicated colleagues engaged in developing the next generation of architecture for high-performance computing

- For this position, you must be currently authorized to work in the United States without the need for sponsorship for a non-immigrant visa. This job was first posted by CyberCoders on 07/29/2026 and applications will be accepted on an ongoing basis until the position is filled or closed. Everforth CyberCoders is proud to be an Equal Opportunity Employer

All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, age, sexual orientation, gender identity or expression, national origin, ancestry, citizenship, genetic information, registered domestic partner status, marital status, status as a crime victim, disability, protected veteran status, or any other characteristic protected by law. Our hiring process includes AI screening for keywords and minimum qualifications, and a virtual recruiter as part of the application process. A human recruiter reviews all results. Click here for details on our virtual recruiter .  Everforth CyberCoders will consider qualified applicants with criminal histories in a manner consistent with the requirements of applicable state and local law, including but not limited to the Los Angeles County Fair Chance Ordinance, the San Francisco Fair Chance Ordinance, and the California Fair Chance Act. Everforth CyberCoders is committed to working with and providing reasonable accommodation to individuals with physical and mental disabilities. Individuals needing special assistance or an accommodation while seeking employment can contact a member of our Human Resources team at  View email address on ziprecruiter.com to make arrangements.

Salary

$200000 - $250000 USD per year