Research Engineer, Interactive World Models - New College Grad 2026

Details

NVIDIA develops technologies in computer graphics, PC gaming, accelerated computing, and artificial intelligence. The FlashDreams and FastGen technologies support real-time world simulations by combining faster, more controllable video models with responsive execution systems. Applications include autonomous-driving simulation, robot policy development and testing, game worlds, medical simulation, and virtual training.

The Research Engineer will contribute across model development and runtime systems, helping turn research into production-ready systems and AI capabilities.

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.
• Work with researchers on few-step distillation, causal or autoregressive generation, reward fine-tuning, action conditioning, and long-horizon spatiotemporal memory and consistency.
• Deliver 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.
• Partner with researchers and users to improve system reliability and adoption.

Requirements

• Experience or coursework in video or world models, diffusion and generative modeling, model distillation and adaptation, simulation, robotics, computer vision, or real-time stateful machine-learning 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.
• Software-engineering fundamentals including design, testing, debugging, version control, performance analysis, and Linux development.
• Ability to turn open-ended technical problems into working implementations, measure quality and performance, and communicate results clearly.

Preferred Qualifications

• Experience with post-training generative video models, including distillation, self-forcing, action conditioning, or long-horizon memory.
• Experience profiling or optimizing machine-learning workloads using CUDA, Triton, TensorRT, torch.compile, or similar tools.
• Experience with latency, throughput, quantization, streaming, state or cache management, or multi-GPU execution.
• Contributions to an open-source machine-learning project or developer platform, including model support, performance improvements, tests and benchmarks, difficult issue resolution, documentation, or user adoption.

Benefits

• Base salary range of $108,000–$178,250 for Level 1.
• Base salary range of $124,000–$195,500 for Level 2.
• Eligibility for equity and benefits.
• NVIDIA offers a comprehensive benefits package.
• Applications will be accepted at least until August 25, 2026.
• NVIDIA is an equal opportunity employer committed to an inclusive work environment.