Research Engineer, Generative Video

Mirage is an AI-native video platform seeking a Research Engineer to build and scale systems powering generative video models. The role focuses on training and optimizing large-scale video and multimodal models, improving inference efficiency, and bringing cutting-edge research models into production. This position sits at the intersection of research and systems engineering, targeting ultra-low latency, real-time generation.

• Train and optimize large-scale video and multimodal models
• Improve efficiency across training and inference (memory, latency, cost)
• Implement techniques such as distillation, quantization, and pruning to accelerate diffusion and autoregressive generation
• Build and maintain distributed training systems
• Optimize GPU utilization, parallelism, and throughput
• Develop tooling for experimentation, evaluation, and debugging
• Translate research models into robust, production-ready systems
• Monitor and improve model performance in real-world usage

• BS/MS/PhD in CS, ML, or related field
• 2+ years of professional industry experience
• Strong experience in deep learning systems and infrastructure
• Expertise in PyTorch, CUDA, Triton, and distributed training (FSDP, etc.)
• Experience scaling and optimizing large models under low-latency inference constraints