Inference Runtime, Engineering Manager

Location:

San Francisco

Compensation:

$455K – $555K/year

Responsibilities:

• Lead a team of engineers specializing in distributed systems and model architecture.
• Collaborate with machine learning researchers and product managers to deploy technologies.
• Improve performance, latency, and efficiency of the model inference stack.
• Optimize code and GPU fleet for maximum resource utilization.

Requirements:

• 15+ years of professional software engineering experience.
• Familiarity with PyTorch, NVidia GPUs, and HPC technologies.
• Experience in architecting and debugging production distributed systems.