Staff Software Engineer, ML Performance & Systems - Remote

Overview

Help fal maintain its frontier position on model performance for generative media models. Design and implement novel approaches to model serving architecture on top of our in-house inference engine, focusing on maximizing throughput while minimizing latency and resource usage. Develop performance monitoring and profiling tools to identify bottlenecks and optimization opportunities. Work closely with our Applied ML team and customers (frontier labs on the media space) and make sure their workloads benefit from our accelerator.

In Short

• Help fal maintain its frontier position on model performance for generative media models.
• Design and implement novel approaches to model serving architecture.
• Focus on maximizing throughput while minimizing latency and resource usage.
• Develop performance monitoring and profiling tools.
• Identify bottlenecks and optimization opportunities.
• Work closely with the Applied ML team and customers.

Requirements

• Strong foundation in systems programming.
• Deep understanding of cutting edge ML infrastructure stack.
• Fundamental view of the underlying hardware.
• Proficient in Triton or willingness to learn.
• Familiar with internals of Ring Attention, FA3, FusedMLP implementations.

Benefits

• Opportunity to work on cutting-edge technology.
• Collaborate with leading experts in the field.
• Flexible working environment.