Senior AI Researcher — Generative Video & Human Motion

NVIDIA; California (MO); On-site; USD 184,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits package

Job summary

NVIDIA in the United States seeks an experienced applied researcher to push the frontier of video generation and human-centric realism. You will explore architecture, diffusion-based approaches, and neural rendering-inspired representations, translating research into production-grade checkpoints and demos.

With 8+ years in vision/graphics and deep learning, you will optimize training/inference, tackle bottlenecks, and collaborate with data, platform, and product teams to deliver real performance

Qualifications

• PhD in Computer Science, Graphics, Computer Engineering, or closely related field (or equivalent experience).
• 8+ years of applied research and/or industry experience in vision, graphics, or related ML domains.
• 3+ years designing, training, evaluating generative models for image/video/audio with deep learning fundamentals.
• Hands-on experience improving generative models focusing on perceptual quality and temporal stability for humans.
• Advanced proficiency in Python, PyTorch, C++, and CUDA with strong research-engineering practices.
• Experience training and debugging large models in multi-GPU/multi-node distributed setups.
• Knowledge of inference/runtime bottlenecks and optimization techniques.
• Strong eye for quality and ability to diagnose visual artifacts with perceptual metrics.

Responsibilities

• Research, implement, and validate model architecture and algorithm changes that improve video generation fidelity with emphasis on human-centric quality.
• Prototype improvements across spatial multimodal modeling, modality alignment, diffusion-based video generation, and neural rendering-inspired representations.
• Improve training and inference efficiency through architectural and post-training optimizations.
• Define model training objectives to improve generalization for human motion, interaction dynamics across real-world and synthetic data.
• Develop benchmarks for evaluating world foundation models in video, simulation, and environments.
• Translate research results into robust implementations like training code, production checkpoints, and demos.

Skills

Python

PyTorch

C++

CUDA

Education

PhD in Computer Science, Graphics, Computer Engineering, or closely related field

Tools

CUDA Toolkit

Job description

NVIDIA in the United States seeks an experienced applied researcher to push the frontier of video generation and human-centric realism. You will explore architecture, diffusion-based approaches, and neural rendering-inspired representations, translating research into production-grade checkpoints and demos.

With 8+ years in vision/graphics and deep learning, you will optimize training/inference, tackle bottlenecks, and collaborate with data, platform, and product teams to deliver real performance