CUDA GPU Kernel Architect for High-Throughput AI

TypeSafe AI; San Francisco (CA); On-site; USD 180,000 - 280,000; Full time

Benefits offered by this job

Base salary $180k–$280k plus equity

100% covered health insurance

Daily lunch and dinner

Visa sponsorships

401K plans

Job summary

TypeSafe AI in San Francisco is seeking a GPU kernel engineer with deep CUDA expertise to accelerate our training and inference workloads. You will write, optimize, and maintain high-performance kernels close to the metal.

Work alongside research and platform engineers to squeeze throughput and reduce latency, with the team operating in-person at our SF office near Embarcadero. This role requires hands-on LLM training experience and a track record of real performance wins.

Qualifications

• Deep CUDA / GPU kernel expertise.
• Experience building and optimizing inference / training kernels.
• Hands-on LLM training experience (not hobbyist).
• Reason from first principles about performance, memory, and parallelism.

Responsibilities

• Write, optimize, and maintain high-performance GPU kernels (e.g., in CUDA / CuTe DSL) for training and inference
• Profile end-to-end performance and eliminate bottlenecks across the stack
• Partner with research and platform engineers to squeeze maximum throughput and minimum latency out of our hardware

Skills

CUDA / GPU kernel expertise

Inference & training kernels

LLM training experience

Performance optimization

Tools

CuTe DSL

CUDA

Job description

TypeSafe AI in San Francisco is seeking a GPU kernel engineer with deep CUDA expertise to accelerate our training and inference workloads. You will write, optimize, and maintain high-performance kernels close to the metal.

Work alongside research and platform engineers to squeeze throughput and reduce latency, with the team operating in-person at our SF office near Embarcadero. This role requires hands-on LLM training experience and a track record of real performance wins.