Machine Learning Infrastructure Engineer Intern

{
  "content_hash": "cc9b5884054c6c65d126a4a98d59da7be083c5f7a2cbaf486a09aac23cfe5b76",
  "source_hash": "60b6270fd50d073993fc00e88cdd2f56e6fd7e56104aaef1c81d620d4c24b584",
  "last_changed_at": "2026-05-29T06:58:18.050Z",
  "active_status": "active"
}

{
  "language": "en",
  "location": {
    "raw": "Santa Clara, CA",
    "city": "Santa Clara",
    "region": "CA",
    "country": "United States",
    "is_remote": false,
    "confidence": 0.9
  },
  "salary_max": 65,
  "salary_min": 19,
  "inferred_at": "2026-06-06T07:56:17.739Z",
  "launch_scope": {
    "reason": "english_us_canada",
    "included": true,
    "language": "en",
    "location": {
      "raw": "Santa Clara, CA",
      "city": "Santa Clara",
      "region": "CA",
      "country": "United States",
      "is_remote": false,
      "confidence": 0.9
    },
    "countries": [
      "United States"
    ]
  },
  "remote_policy": null,
  "salary_period": "hour",
  "workplace_type": "on_site",
  "salary_currency": "USD"
}

{}

{
  "lists": [
    {
      "text": "Responsibilities:",
      "content": "\n<li><span data-sheets-root=\"1\">Identify Training Bottlenecks: Profile and analyze Bird's Eye View (BEV) model training pipelines to pinpoint computational and memory bottlenecks.</span></li>\n<li><span data-sheets-root=\"1\">Develop Custom Kernels: Design and implement high-performance custom compute kernels using CUDA, Triton, or C++ to accelerate the model training process.</span></li>\n<li><span data-sheets-root=\"1\">Leverage LLMs for Optimization: Explore and integrate Large Language Models (LLMs) to assist in generating high-performance code and optimizing kernel logic.</span></li>\n<li><span data-sheets-root=\"1\">Automate Profiling Workflows: Build systems to automate performance profiling and analysis using tools like NVIDIA Nsight and the PyTorch Profiler.</span></li>\n<li><span data-sheets-root=\"1\">Iterative Performance Tuning: Continuously analyze profiling data generated by both human and LLM-assisted workflows to maximize GPU utilization and reduce training times.</span></li>\n"
    },
    {
      "text": "Required Skills:",
      "content": "\n<li><span data-sheets-root=\"1\">Systems Programming: Strong proficiency in C++ and a solid understanding of memory management, computer architecture, and parallel processing principles.</span></li>\n<li><span data-sheets-root=\"1\">Deep Learning Frameworks: Hands-on experience with PyTorch, specifically understanding custom operations, autograd, and training loops.</span></li>\n<li><span data-sheets-root=\"1\">Performance-Oriented Mindset: Strong problem-solving skills with a deep interest in performance tuning, algorithmic efficiency, and low-level system optimization.</span></li>\n"
    },
    {
      "text": "Preferred Skills:",
      "content": "\n<li><span data-sheets-root=\"1\">GPU Programming Experience: Practical experience writing and optimizing custom GPU kernels using CUDA or OpenAI Triton.</span></li>\n<li><span data-sheets-root=\"1\">Hardware Profiling Tools: Familiarity with hardware and software profiling tools, particularly NVIDIA Nsight (Systems/Compute) and the PyTorch Profiler.</span></li>\n<li><span data-sheets-root=\"1\">LLM for Code Generation: Experience using or prompting LLMs for code writing, refactoring, or exploring AI-assisted software development workflows.</span></li>\n<li><span data-sheets-root=\"1\">Autonomous Vehicle Perception: A foundational understanding of Bird's Eye View (BEV) models, 3D perception, or spatial transformers used in autonomous driving.</span></li>\n"
    }
  ],
  "country": "US",
  "createdAt": 1778811789495,
  "updatedAt": null,
  "categories": {
    "team": "Data",
    "location": "Santa Clara, CA",
    "commitment": "Intern",
    "department": "US Internships",
    "allLocations": [
      "Santa Clara, CA"
    ]
  },
  "salaryRange": {
    "max": 65,
    "min": 19,
    "currency": "USD",
    "interval": "per-hour-wage"
  },
  "workplaceType": "onsite"
}