Generative Video Research Engineer — Real-Time ML Systems

Doist; New York (NY); On-site; USD 150,000 - 230,000; Full time

Benefits offered by this job

Comprehensive medical/dental/vision

401K with employer match

Commuter Benefits

Catered lunch several days a week

Dinner stipend and Grubhub

Health & Wellness Perks

Team offsites

Generous PTO

Job summary

Mirage seeks an ML Engineer to build and scale video generation models with ultra-low latency. You’ll work at the intersection of research and systems engineering, optimizing training and inference while pushing production‑ready capabilities.

Join an interdisciplinary team tackling hard challenges in generative media, with in-person work at our NYC HQ and a focus on scalable, efficient model deployment.

Qualifications

• BS/MS/PhD in CS, ML, or related field.
• 2+ years of professional industry experience.
• Strong experience in deep learning systems and infrastructure.
• 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.

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

Skills

Deep learning systems

Distributed training

Performance profiling

Debugging

Production deployment

Education

BS/MS/PhD in CS, ML, or related field

Tools

PyTorch

CUDA

Triton

FSDP

Job description

Mirage seeks an ML Engineer to build and scale video generation models with ultra-low latency. You’ll work at the intersection of research and systems engineering, optimizing training and inference while pushing production‑ready capabilities.

Join an interdisciplinary team tackling hard challenges in generative media, with in-person work at our NYC HQ and a focus on scalable, efficient model deployment.