Research Engineer: Real-Time AI World Models & Systems

NVIDIA; Santa Clara (CA); On-site; USD 108,000 - 196,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking a Research Engineer to contribute across model development and runtime systems, focusing on real-time, stateful ML workloads and production-ready world models. You’ll work with researchers to advance diffusion and autoregressive capabilities, and help ship research into scalable systems with GPUs and distributed runtimes.

The role emphasizes strong Python/PyTorch skills, software engineering fundamentals, and the ability to transform open-ended problems into working

Qualifications

• Experience or coursework in one or more areas such as video or world models, diffusion and generative modeling, model distillation and adaptation, simulation, robotics, computer vision, or real-time, stateful ML systems.
• Pursuing or recently completed a BS, MS or PhD in Computer Science, Computer Engineering, Electrical Engineering, or a related field or equivalent experience.
• Hands-on experience building, evaluating, integrating, optimizing, or serving machine-learning systems through internships, academic research, open-source work, or substantial projects.
• Strong Python and PyTorch skills, supported by software-engineering fundamentals in design, testing, debugging, version control, performance analysis, and Linux development.
• Ability to turn an open-ended technical problem into a working implementation, measure its quality and performance, and communicate the results clearly.

Responsibilities

• Contribute to building and optimizing 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-of-light.
• Help advance the production-ready world model frontier by working with researchers on few-step distillation, causal or autoregressive generation, reward fine-tuning, action conditioning, and long-horizon spatiotemporal memory and consistency.
• Deliver capabilities such as multi-user experiences and simulation workflows from prototype through evaluation, integration, and release.
• Strengthen the open-source platform through testing, CI/CD, observability, documentation, and developer workflows, and partner with researchers and users to improve reliability and adoption.

Skills

Python

PyTorch

Software engineering

Performance analysis

Linux development

Education

BS/MS/PhD in CS/CE/EE

Tools

CUDA

Triton

TensorRT

Job description

NVIDIA is seeking a Research Engineer to contribute across model development and runtime systems, focusing on real-time, stateful ML workloads and production-ready world models. You’ll work with researchers to advance diffusion and autoregressive capabilities, and help ship research into scalable systems with GPUs and distributed runtimes.

The role emphasizes strong Python/PyTorch skills, software engineering fundamentals, and the ability to transform open-ended problems into working