$224,000 - $356,500 USD yearly
Originally posted June 23, 2026 by the employer. Relisted by the employer on October 31, 2026.
About the role
This role operates at the applied-research boundary, developing and validating model improvements and hardening them into production-grade checkpoints and recipes for world foundation models. The technical focus centers on human appearance, motion, and action understanding for high-fidelity, temporally stable video and world generation.
What you'll do
- Research, implement, and validate model architecture and algorithm changes that improve video generation fidelity, with an 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.
- Improve training and inference efficiency using compute/memory optimizations, distillation, pruning, and compression.
- Define model training objectives that improve sim-to-real and real-to-sim generalization for human motion, contact, and interaction dynamics across real-world and synthetic data.
- Develop domain-specific benchmarks for evaluating world foundation models reasoning about video, simulation, and physical environments.
- Translate research results into robust training code, production-grade checkpoints, model integrations, and demonstration systems.
What you'll need
- PhD in Computer Science, Graphics, Computer Engineering, or a closely related field (or equivalent experience).
- 8+ years of applied research or industry experience in vision, graphics, or adjacent ML domains.
- 3+ years of direct experience designing, training, and evaluating generative models for image, video, or audio.
- 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 experience in reproducibility, testing, profiling, and experiment tracking.
- Experience training and debugging large models in multi-GPU and multi-node environments and distributed training workflows.
- Practical knowledge of inference/runtime bottlenecks and optimization techniques.
Skills: AI systems, world foundation models, video generation, generative models, PyTorch, distributed training
More semiconductor jobs: NVIDIA jobs · Software engineer jobs
Tracked in our index since 5 May 2026. This is our observation date, not the employer posting date. Specialty: Software Engineering Semiconductor (AI ML Hardware). 129 active roles in this specialty at 38 employers in our index, as of 22 Nov 2026.
How we counted: postings read from employer career sites. How we count