Sonatus

Staff Machine Learning Engineer

Sonatus
Apply
8 days ago
Sunnyvale, CA, USAStaff+

Base Salary

$198k - $272k/yr

Responsibilities

  • Build and train Edge AI models, including Transformers, LLMs, CNNs, LSTMs, and tree-based models, for logs, traces, and multimodal vehicle data.
  • Integrate ML workflows and cloud-based LLM APIs, including Gemini, OpenAI, and Claude, with an emphasis on synthetic data generation.
  • Develop clustering and anomaly-detection algorithms to identify log patterns, software regressions, race conditions, crash precursors, and vehicle health issues.
  • Design supervised and unsupervised models for time-series data from CAN bus systems and onboard sensors.
  • Correlate anomalies across vehicle signals, sensor data, and system events to identify root causes.
  • Port and optimize PyTorch and TensorFlow models for production execution on CPU, GPU, and embedded NPU targets.
  • Apply quantization, pruning, distillation, and memory optimization to meet RAM and Flash constraints.
  • Define on-device data filtering and determine which data is processed locally versus in the cloud.
  • Lead Edge ML pipeline architecture and mentor junior engineers on embedded AI best practices.

Requirements

  • Bachelor’s degree in Computer Science, Electrical Engineering, Software Engineering, or a related field.
  • At least 7 years of Machine Learning Engineering experience, including at least 3 years focused on Edge AI or embedded systems.
  • Proven experience mentoring junior engineers and leading technical projects from concept through production.
  • Expert Python and working knowledge of modern C++, including C++14/17 for inference.
  • Deep proficiency with PyTorch or TensorFlow and experience with ONNX, TFLite, or TVM inference engines.
  • Experience with NLP, sequence modeling, vector stores, lightweight LLMs or SLMs, and anomaly-detection libraries such as scikit-learn, tslearn, or statsmodels.
  • Experience deploying to ARM-based Edge environments, manually managing memory, and working with limited compute resources.
  • Strong communication skills and the ability to explain technical trade-offs to stakeholders.
  • A strong Computer Vision or ADAS background is encouraged.
  • A master’s or PhD in Computer Science, Engineering, or a related field is desired.
  • Familiarity with automotive formats and protocols including CAN, DBC, UDS, SOME/IP, or MQTT is desired.
  • Understanding of Linux and QNX kernel logs, dmesg, process states, and OS-level debugging is desired.
  • Experience with NVIDIA TensorRT or Qualcomm SNPE is desired.

Benefits

  • Medical, dental, and vision coverage.
  • Flexible and Dependent Care Expense program.
  • 401(k) retirement plan.
  • Basic, voluntary, and AD&D life insurance.
  • Unlimited paid time off and 14 or more paid holidays.
  • Hybrid work arrangement in Sunnyvale, California, with three days per week in the office.
  • Complimentary lunches, snacks, and beverages on onsite working days.
  • Wellness benefit allowance.
  • Phone and internet reimbursement.
  • Computer accessory allowance.

Tech Stack

C++LinuxPythonPyTorchscikit-learnTensorFlow
Sonatus

About Sonatus

201-500 employees
Contact me