Senior AI Runtime Engineer: Scale GPU Training

Cacheflow; San Francisco (CA); On-site; USD 160,000 - 225,000; Full time

Benefits offered by this job

Equity

Annual performance bonus

Comprehensive benefits package

Job summary

Cacheflow is seeking a Senior Software Engineer for AI Runtime at Databricks, located in San Francisco. You will be instrumental in building and scaling systems for large-scale GPU training, ensuring high throughput and resilience in training across expansive fleets of accelerators.

The role demands 5+ years of experience in distributed systems, proficiency with GPU training infrastructure, and a commitment to driving engineering excellence. The pay range is between $160,000 and $225,000 USD.

Qualifications

• 5+ years of experience building and operating large-scale distributed systems.
• Strong understanding of training resilience patterns.
• Proven ability to deliver technically complex projects.

Responsibilities

• Drive the architecture and evolution of AIR's managed GPU training platform.
• Solve large-scale training challenges, including orchestration and performance.
• Champion engineering excellence and mentor engineers.

Skills

Large-scale distributed systems

GPU training infrastructure

High-performance computing

ML systems

Distributed training frameworks

Algorithms and data structures

System design

Education

BS in Computer Science or related field

MS or PhD preferred

Job description

Cacheflow is seeking a Senior Software Engineer for AI Runtime at Databricks, located in San Francisco. You will be instrumental in building and scaling systems for large-scale GPU training, ensuring high throughput and resilience in training across expansive fleets of accelerators.

The role demands 5+ years of experience in distributed systems, proficiency with GPU training infrastructure, and a commitment to driving engineering excellence. The pay range is between $160,000 and $225,000 USD.