Performance Modeling Engineer, AI Inference Deployments

Skills

About the Role

You will own the tools that tell customers how a model will run on Positron hardware at scale. You will work with customers and product to turn deployment questions into quantified studies, model deployment topologies and network layers, build analytical and simulation-based models on chip simulators, validate against hardware, and deliver a standalone estimation tool.

Requirements

• 5+ years in performance modeling, capacity planning or systems architecture for large-scale AI inference, HPC or data-center systems
• Experience building analytical or queueing performance models and calibrating them
• Deep understanding of LLM inference at systems level
• Working knowledge of data-center networking and GPU performance
• Comfort with incomplete information and stating assumptions
• Strong Rust skills or expert C/C++ with willingness to use Rust, and Python proficiency
• Excellent communication skills

Responsibilities

• Partner with customers and product to turn deployment questions into focused studies
• Run apples-to-apples comparisons against competitor hardware
• Design and deliver a standalone performance-estimation tool for customers
• Model deployment topologies including tensor, pipeline, expert and data parallelism, batching and mixed Positron-plus-GPU configurations
• Model network and system layers including interconnect latency, bandwidth and redundancy
• Develop analytical and simulation-based deployment models on the chip performance simulator
• Validate projections against measured hardware runs and keep models calibrated

Benefits

• Fully company-paid medical, dental and vision insurance for you and dependents
• Company-paid life and disability coverage
• Supplemental hospital, critical illness and accident coverage available
• Unlimited paid time off
• 13 paid company holidays
• Remote-first culture with company-provided computer and home office setup
• Equity
• 401(k) with company matching from day one