Staff ML Inference Engineer Model Efficiency (Remote)

Jaide Health is seeking an engineer for their Model Efficiency team in San Francisco. The role focuses on building reliable ML systems while enhancing core performance metrics across model execution. You'll work with advanced performance techniques such as GPU/CUDA optimizations and collaborate closely with modeling and systems teams. Ideal candidates will have over 5 years of experience in high-performance coding, plus strong skills in C++ or Python and insights into the LLM inference ecosystem. A commitment to diversity and inclusive work culture is celebrated. #J-18808-Ljbffr Jaide Health