ML Performance Engineer

Location: New York or San Francisco, United States

Salary: $200,000–$350,000 annually, plus equity

Company

hirify.global is building infrastructure for AI workloads, providing instant GPU access, fast container starts, native storage, production-ready sandboxes, and low-latency model inference at scale.

What you will do

• Improve the performance and scalability of ML systems.
• Contribute to open-source projects and hirify.global’s container runtime.
• Optimize language and diffusion model workloads for higher throughput and lower latency.
• Investigate GPU performance bottlenecks, including SM occupancy and host overhead.
• Rewrite algorithms and systems components to improve compute efficiency.

Requirements

• 5+ years of experience writing high-quality, high-performance code.
• Experience with Torch, high-level ML frameworks, and inference engines such as vLLM or TensorRT.
• Familiarity with Nvidia GPU architecture and CUDA.
• Experience with ML performance engineering and demonstrated GPU performance optimization results.

Nice to have

• Familiarity with low-level operating system foundations, including the Linux kernel, file systems, and containers.

Culture & Benefits

• Opportunity to contribute to open-source projects.
• Work alongside researchers, open-source creators, and experienced engineering and product leaders.
• Equity included in the compensation package.