Member of Technical Staff - ML Performance

Modal•San Francisco, CA

About The Position

Modal provides the infrastructure foundation for AI teams, offering instant GPU access, sub-second container startups, and native storage to simplify model training, batch job execution, and low-latency inference. They serve thousands of customers for production AI workloads, including Lovable, Scale AI, Substack, and Suno. Modal is a fast-growing team based in NYC, SF, and Stockholm, having achieved 9-figure ARR and recently raised a Series B at a $1.1B valuation with investors like Lux Capital, Redpoint Ventures, Amplify Partners, and Elad Gil. Joining Modal means becoming part of a rapidly expanding AI infrastructure organization at an early stage, with significant growth opportunities. The team comprises creators of popular open-source projects (e.g., Seaborn, Luigi), academic researchers, international olympiad medalists, and experienced engineering and product leaders. The company is seeking strong engineers experienced in optimizing ML systems for performance at scale, specifically to contribute to open-source projects and Modal’s container runtime to enhance throughput and reduce latency for language and diffusion models.

Requirements

5+ years of experience writing high-quality, high-performance code.
Experience working with torch, high-level ML frameworks, and inference engines (vLLM or TensorRT).
Familiarity with Nvidia GPU architecture and CUDA.
Experience with ML performance engineering (e.g., debugging SM occupancy issues, rewriting an algorithm to be compute-bound, eliminating host overhead).