Senior AI Researcher - World Foundation Models
$184k - $357k • Remote • US, CA, Remote
Posted 1d ago
Job Location
US, CA, Remote
Tech Stack
Remote Work Policy
Fully remote
Categories
AI Research Engineer
About the job
NVIDIA is developing advanced AI systems capable of perceiving, reasoning about, and generating dynamic worlds. Our team focuses on advancing world foundation models to create high-fidelity, temporally stable video and world generation for applications in Physical AI, simulation, and interactive experiences. This role sits at the intersection of applied research and production, involving the development and validation of model improvements, and their subsequent hardening into production-ready checkpoints and recipes for other teams to utilize. The primary technical focus is on understanding human appearance, motion, and action, with progress measured through rigorous experimentation, diagnostics, and comparative evaluations. Collaboration with data, platform, and product engineering teams is essential to ensure research advancements translate into tangible performance and quality improvements.
Responsibilities
- Research, implement, and validate model architecture and algorithm changes to enhance video generation fidelity, with a focus on human-centric quality.
- Explore and prototype improvements in spatial multimodal modeling, modality alignment, flow-based or diffusion-based video generation, and neural rendering representations to boost controllability and long-horizon consistency.
- Enhance training and inference efficiency using architectural and post-training techniques such as compute/memory optimizations, distillation, pruning, and compression.
- Define model training objectives to improve sim-to-real and real-to-sim generalization, particularly for human motion, contact, and interaction dynamics across real-world and synthetic data.
- Develop detailed, domain-specific benchmarks for evaluating world foundation models, especially those that reason about video, simulation, and physical environments.
- Translate research outcomes into robust implementations, including training code, production-grade checkpoints, model integrations, and demos that showcase capability gains.
Requirements
- PhD in Computer Science, Graphics, Computer Engineering, or a related field, or equivalent experience.
- 8+ years of applied research and/or industry experience in vision, graphics, or adjacent ML domains.
- 3+ years of direct experience designing, training, and evaluating generative models for image/video/audio, with strong deep learning fundamentals.
- 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.
Benefits
- Highly competitive salaries
- Comprehensive benefits package
- Equity