Research Engineer, Video Generation

Mirage•New York, NY

6d•Onsite

About The Position

Mirage is seeking a Research Engineer to build and scale the systems powering our video generation models. You’ll work closely with researchers to optimize performance, improve efficiency, and bring cutting-edge models into production. This role sits at the intersection of research and systems engineering, focusing on making advanced models faster, more efficient, and capable of ultra-low latency, real-time generation.

Requirements

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
Strong debugging and performance profiling skills
Ability to move quickly from prototype to production
Strong software engineering fundamentals

Responsibilities

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 aggressively 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