Description
HiringCafe.com is hiring a founding ML engineer to build and operate production AI and machine learning systems. The role focuses on deploying researcher-trained models, profiling and optimizing inference latency, throughput, memory, and compute, implementing quantization and other optimization techniques, building scalable multi-GPU serving systems, and designing reliable architectures for millions of users. The position is based in Cupertino and requires in-person work, with health, dental, vision, parental leave, and relocation support.
