Poolside is seeking an engineer to optimize GPU utilization and deliver a stable, scalable inference serving stack for researchers. You will partner with the inference and scalability teams to improve throughput, latency, and fault tolerance across large-scale training environments.
You’ll collaborate closely with the infra team to ensure GPU nodes are healthy and fully utilized, enabling faster experimentation and pushing Poolside toward its AGI-focused mission.
#J-18808-Ljbffr