Performance Modeling Engineer (AI)

TL;DR

Performance Modeling Engineer (AI): Developing performance and functional models for rack-level AI inference systems with an accent on processor simulators and hardware-software co-design. Focus on modeling microarchitectural components and analyzing simulation results to inform architecture tradeoffs.

Location: Onsite in Santa Clara, CA

Salary: $200,000–$350,000

Company

A VC-backed, stealth-mode startup building rack-level AI inference systems to maximize efficiency for data center-scale serving.

What you will do

• Design, implement, and maintain processor simulators, including performance and functional models.
• Model microarchitectural components such as pipelines, memory hierarchy, interconnects, and accelerators.
• Generate and curate traces to support targeted performance analysis goals.
• Analyze simulation results to inform architecture tradeoffs and optimizations.
• Collaborate closely with architecture, hardware, and compiler teams.
• Own critical simulation infrastructure from concept through production use.

Requirements

• 5+ years of software engineering experience, ideally in systems, architecture, or EDA domains.
• Strong C++ and Python skills with experience in large, complex codebases.
• Experience with processor simulators, architectural modeling, or from-scratch simulator development.
• Solid understanding of computer architecture and microarchitecture.
• Ability to work independently in an early-stage startup environment.
• Location: Must work onsite in Santa Clara, CA

Nice to have

• Experience with AI/ML accelerators, GPUs, or heterogeneous systems.
• Familiarity with simulators such as gem5, gem5-SALAM, or proprietary modeling tools.
• Background in hardware-software co-design or compilers.