Research Engineer - World Modeling

{
  "content_hash": "d3baebb9eae1fb9d662535b0a28dd28f8d5ccb7a608d8ad2a1bc1afe22a34bd4",
  "source_hash": "80059fa25873eddb02c53b4a499fea57ed0649f13de5bde8d9a3d64599fcb817",
  "last_changed_at": "2026-05-31T10:34:25.394Z",
  "active_status": "deleted"
}

{
  "language": "en",
  "location": {
    "raw": "Sunnyvale, CA",
    "city": "Sunnyvale",
    "region": "CA",
    "country": "United States",
    "is_remote": false,
    "confidence": 0.9
  },
  "salary_max": 450000,
  "salary_min": 150000,
  "inferred_at": "2026-05-29T06:59:53.120Z",
  "launch_scope": {
    "reason": "english_us_canada",
    "included": true,
    "language": "en",
    "location": {
      "raw": "Sunnyvale, CA",
      "city": "Sunnyvale",
      "region": "CA",
      "country": "United States",
      "is_remote": false,
      "confidence": 0.9
    },
    "countries": [
      "United States"
    ]
  },
  "remote_policy": null,
  "salary_period": "year",
  "workplace_type": "on_site",
  "salary_currency": "USD"
}

{}

{
  "lists": [
    {
      "text": "Key Responsibilities: Data Infrastructure & Pipelines",
      "content": "<li>Design, implement, and maintain scalable video data pipelines to support large-scale training.&nbsp;</li><li>Develop data preprocessing, transformation, and synthesis workflows to support world model training.&nbsp;</li><li>Contribute to building high-quality data annotation pipelines to ensure accurate and consistent labels across large-scale datasets.&nbsp;</li>"
    },
    {
      "text": "Key Responsibilities: Training & Inference Systems",
      "content": "<li>Support the training of multimodal foundation models (e.g., video diffusion models, world models) by developing and optimizing distributed training systems.&nbsp;</li><li>Improve inference and serving efficiency for real-time interaction through model optimization and system tuning.&nbsp;</li><li>Monitor system health and performance, and contribute to debugging and optimization at scale.&nbsp;</li>"
    },
    {
      "text": "Key Responsibilities: Collaboration & Integration",
      "content": "<li>Work closely with research teams to understand experimental goals and translate ideas into reliable and maintainable infrastructure and tools.&nbsp;</li><li>Integrate novel research prototypes into production-ready systems and ensure reproducibility at scale.&nbsp;</li><li>Participate in design and code reviews, ensuring code quality, efficiency, and compliance with best practices.&nbsp;</li>"
    },
    {
      "text": "Key Responsibilities: Benchmarking & Evaluation",
      "content": "<li>Contribute to the development of tools and infrastructure to evaluate model performance using rigorous quantitative benchmarks, including metrics for physical accuracy and controllability.&nbsp;</li>"
    },
    {
      "text": "Key Responsibilities: Codebase & Documentation",
      "content": "<li>Maintain and extend shared codebases, contribute to internal documentation, and support onboarding of new team members or collaborators.&nbsp;</li><li>Write clean, efficient, and well-tested code for components across the model development lifecycle.&nbsp;</li>"
    },
    {
      "text": "Key Responsibilities",
      "content": "<li>Support contributions to research papers and demos when engineering work plays a significant role.&nbsp;</li><li>Help represent the team’s engineering excellence in internal and external forums when appropriate.&nbsp;</li>"
    },
    {
      "text": "Academic Qualifications",
      "content": "<li>MSc or PhD in Machine Learning or Computer Science, or equivalent industry experience.&nbsp;</li>"
    },
    {
      "text": "Professional Experience Required",
      "content": "<li>Proficient in data collection, cleaning, and transformation at scale, including designing robust pipelines for multimodal datasets (e.g., video, audio, text).&nbsp;</li><li>Practical experience with web scraping and crawling frameworks (e.g., scrapy, selenium, playwright, BeautifulSoup) to collect and curate high-quality web-scale datasets.&nbsp;</li><li>Experience in large-scale model training (LLMs or Diffusion Models) on large clusters.&nbsp;</li><li>Hands-on experience with state-of-the-art video generative models (e.g., Sora, Veo2, MovieGen, CogVideoX, etc.).&nbsp;</li><li>Experiences in building and optimizing large-scale video data pipelines.&nbsp;</li><li>Experience in accelerating diffusion model inference for improved efficiency.&nbsp;</li><li>Exceptional problem-solving and troubleshooting skills to tackle complex technical challenges.&nbsp;</li><li>Strong systems and engineering expertise in deep learning frameworks such as PyTorch.&nbsp;</li><li>Strong communication and collaboration skills for effective cross-functional teamwork.&nbsp;</li><li>Demonstrated ability to solve complex system-level challenges and debug failures across the training/inference stack (e.g., memory issues, deadlocks, I/O bottlenecks).</li>"
    }
  ],
  "country": "US",
  "createdAt": 1746216699428,
  "updatedAt": null,
  "categories": {
    "team": "Engineering",
    "location": "Sunnyvale, CA",
    "commitment": "Full-time",
    "allLocations": [
      "Sunnyvale, CA"
    ]
  },
  "salaryRange": {
    "max": 450000,
    "min": 150000,
    "currency": "USD",
    "interval": "per-year-salary"
  },
  "workplaceType": "onsite"
}