Senior Research Engineer, Interactive World Models

NVIDIA
Santa Clara
Workplace: OnsiteFull timeUSD 184,000 - 356,500 annuallyFunction: Research & Scientific (R&D)Skills: ["Research and engineering judgment","Problem-solving","Delivery","Collaboration"]

Lead engineering that turns video-model research into real-time world simulations. Build and optimize stateful autoregressive serving with per-step controls, KV-cache/state management, GPU inference, and low-latency streaming. Collaborate with researchers to advance few-step distillation, reward fine-tuning, action conditioning, and long-horizon spatiotemporal consistency. Deliver multi-user simulation workflows from prototype to evaluation and release.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
NVIDIA
NVIDIA
3 days ago

Senior Research Engineer, Interactive World Models

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 1 hour agoStatus: Live

Job Summary

Lead engineering that turns video-model research into real-time world simulations. Build and optimize stateful autoregressive serving with per-step controls, KV-cache/state management, GPU inference, and low-latency streaming. Collaborate with researchers to advance few-step distillation, reward fine-tuning, action conditioning, and long-horizon spatiotemporal consistency. Deliver multi-user simulation workflows from prototype to evaluation and release.
Location: Santa Clara
Workplace: Onsite
Employment Type: Full time
Job Function: Research & Scientific (R&D)
Seniority: Mid level

Key Responsibilities

  • •Build and optimize a continuous autoregressive serving loop with per-step control inputs, model/KV-cache state management, GPU inference, frame streaming, and model integrations.
  • •Advance production-ready world model capabilities with few-step distillation, causal/autoregressive generation, reward fine-tuning, action conditioning, and long-horizon spatiotemporal memory and consistency.
  • •Lead end-to-end delivery of multi-user experiences and simulation workflows from prototype through evaluation, integration, and release.
  • •Partner with applied researchers and domain teams to meet quality, performance, and reliability goals.

Pay and Benefits

Salary: USD 184,000 - 356,500 annually
Equity and Bonus:Equity

Key Requirements

  • •Experience in video/world models, diffusion/generative modeling, model distillation/adaptation, simulation/robotics, computer vision, or real-time stateful ML systems.
  • •MS or PhD in Computer Science, Electrical Engineering, or a related field (or equivalent experience).
  • •5+ years of equivalent applied ML or research engineering experience.
  • •Track record advancing applied ML/ML systems from research through thorough evaluation and release, including open-source software, patents, or deployed technology.
  • •Hands-on experience with Python, PyTorch, and GPU-accelerated training/inference with performance optimization or serving.
Experience:World modelsVideo modelsDiffusionGenerative modelingSimulationRoboticsComputer visionStateful MLOpen-source
Education:
Skills:Research and engineering judgmentProblem-solvingDeliveryCollaboration
Tech Stack:PythonPyTorchGPUGPU kernelsQuantizationKV-cacheVLLMSGLangFastVideoLightX2VDiffusersFlashInfer

Company Brief

NVIDIA
Designs and manufactures GPUs, AI accelerators, and system-on-chip products for gaming, data centers, professional visualization, and automotive markets, enabling advanced graphics, AI, and high-performance computing solutions worldwide.
Industry: Electronics Manufacturing
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Public Company
Valuation: Public Company (Market Cap in USD)
Funding: IPO / Publicly Listed
Headquarters: Santa Clara, United States
Founded: 1993
Glassdoor
Glassdoor: 4.3
WebsiteLinkedInGlassdoor