ASIC Engineer, Performance Architecture and Modeling
Meta PlatformsJob Title
ASIC Engineer, Performance Architecture and Modeling
Role Summary
Work on performance and modeling for custom infrastructure ASICs used in AI and data-center systems. The role defines performance analysis approaches, builds pre-silicon models, and coordinates across architecture, RTL, physical design, and software teams to meet throughput, latency, and efficiency targets.
Experience Level
Senior — the posting specifies 8+ years of experience in ASIC design or silicon engineering and 5+ years in performance modeling or pre-silicon simulation.
Responsibilities
Primary responsibilities include ownership of performance modeling and cross-functional alignment.
- Define and own performance modeling strategy for custom infrastructure ASICs.
- Drive microarchitectural exploration and trade-off analysis.
- Develop and validate pre-silicon performance models (cycle-accurate / transaction-level).
- Create low-level workloads and kernels for machine-learning and data-center workloads.
- Establish benchmarking frameworks and performance analysis methodologies.
- Collaborate with architecture, RTL, and physical design teams to translate performance targets into specifications.
- Partner with software and firmware teams to optimize scheduling and runtime against silicon performance.
- Lead technical reviews, report modeling results to leadership, and define long-term modeling infrastructure roadmaps.
- Mentor engineers on performance modeling techniques and resolve performance gaps via root-cause analysis.
Requirements
Must-have technical skills and experience; items labeled "Nice-to-have" are preferred but not strictly required.
- Must-have: 8+ years in ASIC design or silicon engineering.
- Must-have: 5+ years in ASIC performance modeling or pre-silicon simulation.
- Must-have: Proficiency in C++ and Python for simulation and tooling.
- Must-have: Experience with cycle-accurate or transaction-level performance models for complex digital systems.
- Must-have: Experience analyzing performance of data-center or AI workloads on custom silicon and defining microarchitectural specifications.
- Must-have: Familiarity with assembly-level programming and compiler technologies.
- Nice-to-have: Experience with SystemC for performance modeling.
- Nice-to-have: Knowledge of SystemVerilog or VHDL and post-silicon performance validation methodologies.
- Nice-to-have: Experience building automation pipelines for simulation and performance analysis and working on hyperscale ASIC infrastructure.
Education Requirements
Bachelor's degree in Computer Science, Computer Engineering, or a related field (stated in the posting). No explicit mention of alternative-equivalent language or required certifications.
About the Company
Company: Meta Platforms
Headquarters: Menlo Park, California, United States
American technology company that develops social networking products (Facebook, Instagram, WhatsApp) and invests in virtual/augmented reality hardware and software through Reality Labs, focusing on connectivity, advertising, and immersive computing experiences.
