Software Engineer, Inference - Performance Optimization

Highlights

• Model inference performance across application, model, and fleet layers.
• Build cost-to-serve estimates from microbenchmarks to guide future launches.
• Turn profiling insights into faster, cheaper production inference systems.

What they offer

• Equity

Ideal candidate

Systems thinker who loves reasoning from first principles across hardware to applications and turning profiling insights into real production gains with research and engineering partners.

Requirements

• Enjoy reasoning from first principles about distributed systems, model inference, and hardware efficiency.
• Are comfortable working across abstraction layers, from application behavior to kernels, accelerators, networking, and fleet scheduling.
• Have deep expertise with performance profiling, benchmarking, analysis, and optimization.
• Enjoy collaborating with engineering and research teams to improve real production systems.