GPU inference optimization jobs

Cloud Inference Engineer

Luminal · Posted Nov 7, 2026

San Francisco, California, United States
On-site
Full-time
$150K–$250K per year

Apply with RefersoAI Apply on careers page

Deploy and tune models with optimizations like KV caching, paged attention, sequence packing, etc. Conduct model performance reviews, improve scheduler, batcher, autoscaling; profile latency, cost, utilization. Occasionally write kernels and engage in tasteful communication.

Compensation

Annual base salary: $150,000–$250,000 USD. Equity: 0.15%–0.75%. Visa: US citizen/visa only.

Responsibilities

Deploy and tune models with optimizations like KV caching, paged attention, sequence packing, etc.
Conduct model performance reviews
Improve scheduler, batcher, autoscaling; profile latency, cost, utilization
Occasionally write kernels and engage in tasteful communication

Skills

CUDA GPU inference optimization vLLM SGLang TensorRT-LLM KV caching paged attention batching token streaming