Remote Founding Engineer - ML Performance

Description:

• uRun is building the inference cloud for interactive AI, enabling real-time, stateful inference at scale.
• As a Founding Engineer - ML Performance, you will optimize performance to achieve 10-100x speed improvements in AI infrastructure.

Requirements:

• Deep expertise in CUDA with experience writing custom kernels in production.
• Strong background in model inference and post-training optimization at scale.
• Fluency in GPU memory hierarchy, warp scheduling, and hardware-aware algorithm design.
• Experience profiling and benchmarking complex inference pipelines.
• Ability to operate independently, identifying problems and implementing solutions.

Benefits:

• Competitive salary and meaningful equity in an early-stage AI infrastructure company.
• Full health, dental, and vision coverage.
• 401(k) with company support for retirement savings.
• Flexible spending accounts (FSA/HSA) for healthcare costs.
• Paid time off with trust in managing your time.
• Access to top-tier AI tools and hardware (MacBook Pro and AirPods).