Senior ML Systems Engineer - GPU Performance

Fdetimes; New York (NY); Sur place; USD 140 000 - 210 000; Plein temps

Résumé du poste

Modal is seeking seasoned engineers to advance ML systems performance at scale. You will contribute to open-source projects and Modal’s container runtime, aiming to push language and diffusion models toward higher throughput and lower latency.

Ideal candidates have 5+ years of experience writing high-quality code, familiarity with torch and ML frameworks, and strong knowledge of NVIDIA GPUs, CUDA, and performance tuning techniques.

Qualifications

• 5+ years of experience writing high-quality, high-performance code.

Responsabilités

• Contribute to open-source projects and Modal’s container runtime to push language and diffusion models toward higher throughput and lower latency.
• Develop and optimize ML systems for scalability on GPUs and modern NVIDIA architectures.

Connaissances

5+ years exp

Torch

ML performance

CUDA

Outils

vLLM

TensorRT

Description du poste

Modal is seeking seasoned engineers to advance ML systems performance at scale. You will contribute to open-source projects and Modal’s container runtime, aiming to push language and diffusion models toward higher throughput and lower latency.

Ideal candidates have 5+ years of experience writing high-quality code, familiarity with torch and ML frameworks, and strong knowledge of NVIDIA GPUs, CUDA, and performance tuning techniques.