Back to jobs
Bounce1mo ago
Solace20d agoBounce1mo ago
OpenRelay
B2BSeed
Member of Technical Staff, Inference
Own the GPU inference serving layer and optimize model performance for high-throughput production workloads.
HybridSan Francisco or SeattleFull-timeSenior
You will own the serving layer, including engine configuration, request routing, and performance optimization during traffic spikes. The role involves bringing new open-weight models to production quickly and ensuring high throughput per GPU.
Similar jobs
Product Engineer, Supply
Software engineer building core infrastructure for a physical luggage storage marketplace.
HybridLisbonFull-timeMid
Senior Backend Engineer
Build backend infrastructure to help patients navigate and advocate for better healthcare outcomes.
RemoteUnited StatesFull-timeSenior
Product Engineer - Growth
Growth engineer executing experiments to scale a physical cloud storage marketplace.
HybridLisbonFull-timeMid