Staff Engineer, AI Optimization

Job Summary

To drive advancements in AI performance, the full-time Staff Engineer, AI Optimization will lead architectural decisions and optimizations for inference services, ensuring maximum throughput and minimal latency in a remote setting.

Key responsibilities

• Lead the technical strategy for benchmarking and performance optimizations at the inference engine and GPU kernel layers
• Engineer solutions for complex performance issues, focusing on attention layer optimizations and advanced parallelization across multi-node GPU clusters
• Act as a subject matter expert on modern GPU families, advising on hardware procurement and software integration

Required qualifications

• 5+ years of experience in high-performance computing or AI infrastructure
• Deep familiarity with the Gen AI landscape, including major model families
• Hands-on experience with attention-layer optimizations and parallelization strategies in distributed GPU environments
• Comprehensive understanding of NVIDIA and AMD GPU architectures and their software ecosystems
• Expert-level proficiency in Triton or CUDA, with contributions to open-source projects