ML Engineer, Generative Video Production & Scale

Mirage; New York (NY); On-site; USD 120,000 - 210,000; Full time

Benefits offered by this job

Medical, dental, vision plans

401(k) with employer match

Commuter Benefits

Catered lunch

Dinner stipend

Grubhub subscription

Wellness perks

Team offsites

Generous PTO

Job summary

Mirage is seeking an ML Engineer to build and scale the systems powering our video generation models. You’ll tackle novel modeling approaches, training objectives, scaling strategies, and inference optimization to 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. In-person work at our NYC HQ is required.

Qualifications

• BS/MS/PhD in CS, ML, or related field.
• 2+ years of professional industry experience.
• Experience in deep learning systems and infrastructure.
• Expertise in PyTorch, CUDA, Triton, and distributed training (FSDP, etc.).
• Experience scaling 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 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

2+ years industry experience

Deep learning systems

PyTorch

CUDA

Triton

Distributed training

Education

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

Tools

FSDP

Job description

Mirage is seeking an ML Engineer to build and scale the systems powering our video generation models. You’ll tackle novel modeling approaches, training objectives, scaling strategies, and inference optimization to 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. In-person work at our NYC HQ is required.