Staff AI Software Engineer, Edge Model Optimization & Deployment

{
  "content_hash": "b862634be715a6c88dca2cb7c531aeda2bef7224f409039e3b764c892f227065",
  "source_hash": "b23e829d07147589ba11e04930c4d00e5d1dee9beab28b6876f4d037a541ffd1",
  "last_changed_at": "2026-05-29T06:56:56.179Z",
  "active_status": "active"
}

{
  "language": "en",
  "location": {
    "raw": "Seattle, WA",
    "city": "Seattle",
    "region": "WA",
    "country": "United States",
    "is_remote": false,
    "confidence": 0.9
  },
  "salary_max": 300000,
  "salary_min": 70000,
  "inferred_at": "2026-06-06T18:40:26.130Z",
  "launch_scope": {
    "reason": "english_us_canada",
    "included": true,
    "language": "en",
    "location": {
      "raw": "Seattle, WA",
      "city": "Seattle",
      "region": "WA",
      "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": "What You’ll Do:",
      "content": "\n<li>Convert and optimize 2D/3D CNNs and Transformer-based models (PyTorch/TensorFlow → ONNX → TensorRT/Triton) for real-time inference on Jetson/Orin platforms.</li>\n<li>Apply model compression techniques—quantization, pruning, distillation, weight sharing—to meet strict constraints on latency, memory, bandwidth, and power.</li>\n<li>Develop custom TensorRT plugins and CUDA kernels for performance-critical components.</li>\n<li>Integrate optimized models into the broader robotic system using ROS nodes and interfaces.</li>\n<li>Build benchmarks, profile and debug end-to-end inference pipelines, and validate performance in real-world robotic scenarios.</li>\n<li>Collaborate closely with AI researchers, robotics engineers, and hardware teams to translate cutting-edge research into robust, deployable edge solutions.</li>\n<li>Ensure the reliability, robustness, and stability of deployed models operating continuously in challenging, resource-constrained environments.</li>\n"
    },
    {
      "text": "What You Have:",
      "content": "\n<li>5+ years of professional experience developing and deploying deep learning models for edge, embedded, or real-time systems.</li>\n<li>PhD in Computer Science, Robotics, Electrical or Computer Engineering, or a closely related technical field.</li>\n<li>Strong proficiency in PyTorch, C++, Python, and CUDA for AI/ML development and model optimization.</li>\n<li>Hands-on experience with TensorRT, ONNX, and Triton, including authoring custom plugins for TensorRT.</li>\n<li>Proven experience applying model optimization techniques such as quantization, pruning, and distillation in production systems.</li>\n<li>Deep understanding of hardware constraints and performance tuning on Jetson / ARM platforms, GPUs, and embedded Linux systems.</li>\n<li>Experience integrating AI models into ROS-based robotic systems.</li>\n<li>Ability to work independently while collaborating effectively in a fast-paced, cross-functional engineering environment.</li>\n"
    },
    {
      "text": "The Extras That Set You Apart:",
      "content": "\n<li>Experience with ROS2.</li>\n<li>Experience writing and optimizing custom CUDA kernels and low-level GPU performance tuning.</li>\n<li>Familiarity with Triton, ML compilers, or compiler-level optimizations for GPU inference.</li>\n<li>Experience with JAX or additional ML frameworks beyond PyTorch.</li>\n<li>Background deploying AI systems on real robots operating in the field, not just offline or in simulation.</li>\n<li>Familiarity with NVIDIA’s edge and robotics ecosystem (e.g., Isaac ROS, DeepStream, JetPack).</li>\n"
    }
  ],
  "country": "US",
  "createdAt": 1770060722430,
  "updatedAt": null,
  "categories": {
    "team": "Autonomy",
    "location": "Seattle, WA",
    "commitment": "Full time",
    "department": "Engineering",
    "allLocations": [
      "Seattle, WA"
    ]
  },
  "salaryRange": {
    "max": 300000,
    "min": 70000,
    "currency": "USD",
    "interval": "per-year-salary"
  },
  "workplaceType": "onsite"
}