Senior AI Researcher: Human-Centric Video & World Models

NVIDIA; Washington; On-site; USD 184,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is building the next generation of AI systems that perceive, reason, and generate dynamic worlds. This role focuses on human appearance, motion and action understanding, translating research into production-grade checkpoints and recipes.

You will work with data, platform, and product engineering to ensure improvements translate into real performance. Join NVIDIA to push the boundaries of world models, with a base salary range reflecting Level 4–5 postings in the United States, and equity

Qualifications

• PhD in Computer Science, Graphics, Computer Engineering, or a closely related field (or equivalent experience).
• 8+ years of applied research and/or industry experience in vision, graphics, or adjacent ML domains or similar area.
• 3+ years of direct experience designing, training, and evaluating generative models for image/video/audio, with strong fundamentals in modern deep learning.
• Hands-on experience improving generative models with a focus on perceptual quality and temporal stability, especially for generating humans.
• Advanced proficiency in Python, PyTorch, C++, and CUDA with strong research-engineering practices (reproducibility, testing, profiling, experiment tracking).
• Experience training and debugging large models in multi-GPU and/or multi-node environments and distributed training workflows
• Practical knowledge of inference/runtime bottlenecks and optimization techniques.
• Strong “eye for quality” and interest in diagnosing visual artifacts using perceptual metrics, human preference signals, or learned evaluators.

Responsibilities

• Research, implement, and validate model architecture and algorithm changes that improve video generation fidelity, with emphasis on human-centric quality.
• Explore and prototype improvements across spatial multimodal modeling, modality alignment, flow-based or diffusion-based video generation, and neural rendering-inspired representations to improve controllability and long-horizon consistency.
• Improve training and inference efficiency through architectural and post-training techniques (compute/memory optimizations, distillation, pruning, and compression).
• Define model training objectives that improve sim-to-real and real-to-sim generalization, especially for human motion, contact, and interaction dynamics across real-world and synthetic/simulation data.
• Develop detailed, domain-specific benchmarks for evaluating world foundation models, especially generation and understanding world models that reason about video, simulation, and physical environments.
• Translate research results into robust implementations like training code, production-grade checkpoints, model integrations, and demos that clearly showcase capability gains across teams.

Skills

Python

PyTorch

C++

CUDA

Distributed training

Experiment tracking

Education

PhD in Computer Science/Graphics/Computer Engineering

Tools

Git

Job description

NVIDIA is building the next generation of AI systems that perceive, reason, and generate dynamic worlds. This role focuses on human appearance, motion and action understanding, translating research into production-grade checkpoints and recipes.

You will work with data, platform, and product engineering to ensure improvements translate into real performance. Join NVIDIA to push the boundaries of world models, with a base salary range reflecting Level 4–5 postings in the United States, and equity