Research Engineer, Real-Time World Models

Nvidia Corporation in; Santa Clara (CA); On-site; USD 152,000 - 242,000; Full time

Benefits offered by this job

Equity

Comprehensive benefits

Job summary

NVIDIA is seeking a Research Engineer to contribute across model development and runtime systems for Interactive World Models. You will help turn research into scalable systems, collaborating with researchers and domain teams to meet quality, performance, and reliability goals, including an emphasis on few-step distillation, causal generation, and action conditioning.

The role focuses on building production-grade, real-time AI capabilities for diverse applications such as autonomous driving

Qualifications

• BS or MS in Computer Science, Computer Engineering, Electrical Engineering, or related field, or equivalent experience.
• 3+ years of relevant experience building, evaluating, integrating, optimizing, or serving machine-learning systems.
• Strong Python and PyTorch skills, with fundamentals in design, testing, debugging, version control, performance analysis, and Linux development.

Responsibilities

• Build and optimize the continuous autoregressive serving loop, including per-step control inputs, model and KV-cache state management, GPU inference, frame streaming, and model integrations to speed up.</li>
• Advance the production-ready world model frontier by working with researchers on distillation, generation, reward fine-tuning, and long-horizon memory and consistency.
• Deliver capabilities such as multi-user experiences and simulation workflows from prototype through evaluation, integration, and release.

Skills

Python

PyTorch

Linux

Software engineering fundamentals

Version control

Performance analysis

Communication of results

Education

BS or MS in Computer Science/Computer Engineering/Electrical Engineering or related field

Tools

Git

Linux development environment

Testing and debugging

Job description

NVIDIA is seeking a Research Engineer to contribute across model development and runtime systems for Interactive World Models. You will help turn research into scalable systems, collaborating with researchers and domain teams to meet quality, performance, and reliability goals, including an emphasis on few-step distillation, causal generation, and action conditioning.

The role focuses on building production-grade, real-time AI capabilities for diverse applications such as autonomous driving