Remote AI Performance Architect GPU & Distributed ML

Bright Vision Technologies is seeking a Model Optimization Engineer to maximize throughput and minimize latency across training and inference for large neural networks. This role is 100% remote from the U.S. and is a full-time direct hire. You will optimize GPU architectures, memory usage, and compiler toolchains, delivering measurable end-to-end performance gains. Collaborate with product, design, engineering, and operations to translate requirements into robust solutions, mentoring junior J-18808-Ljbffr