Mirage
Research Engineer, Generative Video
About this role
Mirage is hiring a Research Engineer to build and optimize large-scale video generation models, focusing on making advanced generative video systems faster, more efficient, and capable of real-time inference. You'll work at the intersection of ML research and systems engineering, translating cutting-edge models into production-ready systems that power an AI-native video platform.
What you'll do
- Train and optimize large-scale video and multimodal generative models
- Improve efficiency across training and inference pipelines (memory, latency, cost)
- Implement model optimization techniques including distillation, quantization, and pruning for diffusion and autoregressive generation
- Build and maintain distributed training systems with focus on GPU utilization and parallelism
- Develop tooling for experimentation, evaluation, and debugging of model performance
- Translate research prototypes into robust, production-ready systems and monitor real-world performance
What they're looking for
- Deep learning systems and infrastructure
- PyTorch and CUDA programming
- Triton optimization and compiler knowledge
- Distributed training frameworks (FSDP, etc.)
- Model optimization (quantization, distillation, pruning)
- Low-latency inference optimization
- Performance profiling and debugging
- Video generation and diffusion/autoregressive model architectures
Benefits
- Comprehensive medical, dental, and vision insurance
- 401K with employer match
- Commuter benefits
- Catered lunch multiple days per week and dinner stipends for late work
- Grubhub subscription and health & wellness perks
- Multiple team offsites annually with monthly team events and generous PTO
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Mirage
Mirage builds an AI-native video platform that leverages generative media and large language models to enable sophisticated video production, editing, and creative workflows. The company is hiring backend engineers, full-stack software engineers, ML engineers, and iOS developers to advance their AI-driven platform and enhance user experiences in web-based and mobile media creation.
View all jobs at MirageLikely interview questions
- Describe your experience optimizing large language or video models for low-latency inference. What techniques did you use and what improvements did you achieve?
- Walk us through how you've profiled and debugged performance bottlenecks in distributed training systems. What tools did you use?