CareerPlan

Research Engineer, Generative Video

Union Square, New York CityFull-time2026-09-28 → 2026-11-19
On-site · United States

Core

Build and scale systems for training and deploying large-scale generative video models with ultra-low latency.

Role type

Senior ML Engineer (Generative Video Systems)

Builds

Production-ready video generation models and distributed training infrastructure

Domain

Generative AI, Video Production, Deep Learning Systems

Deliverable

production ML models

Required skills

Deep learning systems, PyTorch, CUDA, Triton, distributed training (FSDP), model optimization (distillation, quantization, pruning), performance profiling

Preferred skills

Low-latency inference optimization, GPU utilization, rapid prototype-to-production transition

Technologies

PyTorch, CUDA, Triton, FSDP

Responsibilities

Train and optimize large-scale video and multimodal models; Improve efficiency across training and inference; Implement techniques such as distillation, quantization, and pruning; 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

Seniority

Senior, hands-on IC