Description
Netflix is hiring a Model Serving Systems Engineer to develop and expand compute infrastructure for serving AI/ML and large language models at scale. The role involves building scalable, robust, high-availability, and high-performance systems; optimizing latency and costs; supporting research-to-production workflows; and collaborating with engineers, product managers, machine learning engineers, and data scientists. Preferred qualifications include experience with distributed ML inference services, Java, Triton Inference Server, TensorRT, Docker, and public clouds such as AWS, Azure, or GCP. The role offers an annual salary range of $466,000 to $750,000, with benefits including health plans, retirement matching, stock options, and paid leave.
