Research Engineer, Generative Video

Build and scale the systems powering generative video models, working at the intersection of ML research and production engineering. Train and optimize large-scale video and multimodal models, improve training and inference efficiency, and accelerate diffusion and autoregressive generation using techniques like distillation, quantization, and pruning. Implement distributed training systems, optimize GPU utilization and throughput, and deliver low-latency, real-time generation.