Member of Technical Staff - ML Performance

Highlights

• Push language and diffusion models toward higher throughput and lower latency.
• Build instant GPU access and sub-second container starts at massive scale.
• Contribute to open-source projects and Modal's container runtime.

What they offer

• Equity

Ideal candidate

Performance-obsessed systems engineer who loves squeezing every ounce from GPUs and thrives making ML inference faster at scale.

Requirements

• 5+ years writing high-quality, high-performance code
• Experience with torch, ML frameworks, and inference engines like vLLM or TensorRT
• Familiarity with Nvidia GPU architecture and CUDA
• Experience with ML performance engineering and GPU optimization
• Nice-to-have: familiarity with Linux kernel, file systems, and containers