Founding ML Inference Engineer: Ultra-Low Latency

A pioneering technology firm in San Francisco is seeking a Founding Engineer for ML Inference. This highly technical role focuses on optimizing real-time generative media models. You'll design novel inference frameworks and work to maintain competitive advantage in ultra-low-latency environments. The ideal candidate has a strong foundation in systems programming and expertise in ML infrastructure tools such as PyTorch and TensorRT. This role promises competitive salary and equity, along with comprehensive health coverage and relocation support. #J-18808-Ljbffr