Member of Technical Staff - ML Performance

Optimizes ML model serving for throughput and latency by working on Modal's container runtime and inference engines like vLLM. Focuses on GPU performance tuning, CUDA kernel work, and system-level bottleneck elimination. This is infrastructure-focused rather than customer-facing, emphasizing deep performance engineering over deployment consulting.

ABOUT US: AI NEEDS A NEW INFRASTRUCTURE LAYER. WE'RE BUILDING IT AT MODAL. Every era of computing brought new workloads that previous infrastructure couldn't support: mainframes, databases, and the cloud. Each time, the company that rebuilt the layer underneath defined the decade. AI is no different, except it touches everything instead of one slice, and the window to build the layer underneath it is open right now. Our customers include category-defining companies like Ramp https://modal.com/blog/how-ramp-built-a-full-context-background-coding-agent-on-modal, Cognition, DoorDash, and Suno. They rely on Modal for instant GPU access, sub-second container starts, and native storage, so it's simple to serve low-latency inference, fine-tune models, and access production-ready sandboxes at scale. We've passed $1B in annualized run rate, up 15x from a year ago. In October 2026 we raised a $750M Series D led by Accel at a $15.75B valuation. Our team includes creators of popular open-source projects (e.g.,Seaborn https://github.com/mwaskom/seaborn,Luigi https://github.com/spotify/luigi), academic researchers, international olympiad medalists, and experienced engineering and product leaders with decades of experience. THE ROLE: We are looking for strong engineers with experience in making ML systems performant at scale. If you are interested in contributing to open-source projects and Modal’s container runtime to push language and diffusion models toward higher throughput and lower latency, we’d love to hear from you! YOU MAY BE A FIT IF: - You have 5+ years of experience writing high-quality, high-performance code - You’ve worked with torch, high-level ML frameworks, and inference engines (vLLM or TensorRT) - You’re familiar with NVIDIA GPU architecture and CUDA - You have experience with ML performance engineering (tell us a story about boosting GPU performance: debugging SM occupancy issues, rewriting an algorithm to be compute-bound, eliminating host overhead, etc.) NICE-TO-HAVE: - Familiarity with low-level operating system foundations (Linux kernel, file systems, containers, etc.)