Distributed Systems Engineer, Data & Inference Platform
San Francisco
Workplace: RemoteFull timeFunction: IT Operations (Systems/Network Admin)Experience: 5+ yearsSkills: ["Communication","Problem-solving","Collaboration"]Build and operate distributed inference systems for large language models and the data pipelines that feed them. You’ll optimize throughput, latency, and cost across GPU fleets, design production-grade Ray Data or Spark pipelines, and own on-call reliability. Collaborate with researchers and ML engineers to take workloads from experimentation to production, ensuring scalable, efficient, and cost-effective inference at petabyte scale.
Loading
Loading job details...
Preparing the role view and application actions.

