Research Engineer, Interactive World Models (New Grad 2026)

Nvidia Corporation in; Santa Clara (CA); On-site; USD 120,000 - 196,000; Full time

Job summary

NVIDIA in Santa Clara, CA is seeking a Research Engineer to advance interactive world models and real-time ML systems. This New College Grad 2026 role combines research with production-oriented engineering, building scalable pipelines and runtimes for generative video models and simulation workloads.

You will work with Python and PyTorch, contribute to model development, optimization, and deployment, and collaborate with researchers to ship impactful AI capabilities across platforms.

Qualifications

• Video/world models, diffusion and generative modeling, or real-time ML systems.
• BS/MS/PhD in CS/CE/EE or related field or equivalent experience.
• Hands-on ML system development via internships, research, or projects.
• Strong Python and PyTorch; software engineering fundamentals.
• Turn open-ended problems into working implementations and measure performance.

Responsibilities

• Build and optimize autoregressive serving loop with per-step inputs, KV-cache state, GPU inference, frame streaming, and model integrations.
• Advance world model frontier with few-step distillation, causal or autoregressive generation, reward fine-tuning, memory management.
• Deliver multi-user experiences and simulation workflows from prototype through release.
• Strengthen open-source platform via testing, CI/CD, observability, docs, and developer workflows.

Skills

Python

PyTorch

Software engineering fundamentals

Linux development

Education

BS/MS/PhD in CS/CE/EE

Tools

CUDA

Triton

TensorRT

Torch

Job description

NVIDIA in Santa Clara, CA is seeking a Research Engineer to advance interactive world models and real-time ML systems. This New College Grad 2026 role combines research with production-oriented engineering, building scalable pipelines and runtimes for generative video models and simulation workloads.

You will work with Python and PyTorch, contribute to model development, optimization, and deployment, and collaborate with researchers to ship impactful AI capabilities across platforms.