Hopper is seeking an inference engineer to enhance latency, throughput, and reliability across our serving stack. You will profile workloads, optimize serving code, and drive changes from development to production.
Based in our San Francisco office, you will work on batching, caching, and scheduling for large language models, and you will build benchmarks to quantify improvements in latency and model quality.
#J-18808-Ljbffr
We would love to welcome a new Inference Engineer: Latency & Scale for Speech Models (SF) to our team in San Francisco, CA, United States.
Full responsibilities and requirements are described in the listing above.
Learn more about the Inference Engineer: Latency & Scale for Speech Models (SF) role in the description above.
We appreciate your interest in this position.
Join Hopper and contribute to our ongoing work.