Modal
Member of Technical Staff - ML Performance
$200K–$350K
New York +1 · Staff · Full-time · Posted Apr 21, 2026
- Location
- New York
San Francisco - Experience
- 5+ years writing high-quality, high-performance code.
About the job
Improve the performance of ML systems at scale by optimizing language and diffusion model throughput and latency across open-source projects and Modal’s container runtime.
What you'll do
- Optimize ML systems for higher throughput and lower latency.
- Contribute to open-source projects and Modal’s container runtime.
- Apply ML performance engineering to improve GPU performance.
What they ask for
- 5+ years of experience writing high-quality, high-performance code.
- Experience with torch, high-level ML frameworks, and inference engines (vLLM or TensorRT).
- Familiarity with NVIDIA GPU architecture and CUDA.
- Experience with ML performance engineering.
Nice to have
- Familiarity with low-level operating system foundations, such as the Linux kernel, file systems, or containers.
Pay
USD $200K – $350K base salary
Tools
torch, vLLM, TensorRT, NVIDIA GPU, CUDA, Linux kernel
AI focus
Optimize language and diffusion models for higher throughput and lower latency.
Model-written summary · the original posting is authoritative