Staff ML Performance Engineer — High-Throughput Inference

fal; San Francisco (CA); On-site; USD 180,000 - 250,000; Full time

Benefits offered by this job

Competitive salary and equity

Visa sponsorship

Health, dental, and vision insurance

Regular team events

Job summary

A tech company in San Francisco is looking for a Staff Software Engineer to enhance model performance for generative media models. The ideal candidate will design advanced model serving architectures, develop performance tools, and collaborate with the Applied ML team. Offering a competitive salary of $180,000 - $250,000 with equity and comprehensive health benefits, this position provides substantial growth opportunities.

Qualifications

• Strong foundation in systems programming with expertise in identifying and fixing bottlenecks.
• Deep understanding of cutting edge ML infrastructure stack including model compilation, quantization, and serving architectures.
• Proficient in Triton or willingness to learn with comparable experience in lower-level accelerator programming.

Responsibilities

• Help maintain frontier position on model performance for generative media models.
• Design and implement novel approaches to model serving architecture.
• Develop performance monitoring and profiling tools.

Skills

Systems programming expertise

ML infrastructure stack knowledge

Multi-dimensional model parallelism

Triton proficiency

Tools

PyTorch

TensorRT

Nvidia systems

Job description

A tech company in San Francisco is looking for a Staff Software Engineer to enhance model performance for generative media models. The ideal candidate will design advanced model serving architectures, develop performance tools, and collaborate with the Applied ML team. Offering a competitive salary of $180,000 - $250,000 with equity and comprehensive health benefits, this position provides substantial growth opportunities.