Performance Modeling Engineer, AI Inference Deployments (Senior/Principal)
Core
Develop advanced performance models and deployment-planning tools to estimate how large-scale AI inference workloads perform on next-generation hardware.
Role type
Senior/Principal Performance Modeling Engineer (AI Inference)
Builds
Standalone performance-estimation tools and deployment-level performance models for large-scale inference systems
Domain
AI Infrastructure / High-Performance Computing / Silicon Architecture
Deliverable
production ML models
Required skills
Performance modeling, Systems architecture, LLM inference systems, Data-center networking, GPU architecture, Rust, Python, Analytical modeling, Benchmarking
Preferred skills
Customer-facing tool development, Infrastructure sizing, TCO analysis
Technologies
Rust, Python, C/C++, Chip performance simulators
Responsibilities
Develop analytical models and customer-facing tools for AI inference performance estimation; Conduct performance comparisons between competing hardware platforms; Model network and system-level performance including interconnect latency and topology; Validate performance projections against actual hardware measurements; Collaborate with chip modeling teams to incorporate new hardware capabilities.
Seniority
Senior/Principal, hands-on IC