Staff Machine Learning Engineer
Core
Lead the development of Edge AI for in-vehicle self-aware health monitoring and prediction by building and deploying AI models that analyze continuous vehicle data (logs, traces, internal signals) to detect and predict sub-system health and anticipate failures in real-time.
Role type
Staff Machine Learning Engineer (Edge AI)
Builds
Production-grade AI models for in-vehicle health monitoring and failure prediction on resource-constrained edge devices.
Domain
Automotive / Edge AI / Embedded Systems
Deliverable
production ML models
Required skills
Edge AI development, Embedded Systems, Python, C++, PyTorch, TensorFlow, Model optimization (quantization, pruning, distillation), Anomaly detection, Time-series analysis, NLP/Sequence modeling, Linux/QNX kernel debugging, ARM-based deployment
Preferred skills
Computer Vision, Automotive protocols (CAN, UDS, SOME/IP, MQTT), NVIDIA TensorRT, Qualcomm SNPE, Synthetic data creation, LLM integration
Technologies
PyTorch, TensorFlow, ONNX, TFLite, TVM, Gemini, OpenAI, Claude, scikit-learn, tslearn, statsmodels, C++14/17
Responsibilities
Build and train AI Edge models (Transformers, LLM, CNN, LSTM) for unstructured data; Develop algorithms to cluster log patterns and detect software regressions; Design unsupervised/supervised learning models for time-series sensor data; Port and optimize models for CPU/GPU/embedded NPUs; Define data strategy for on-device filtering; Lead edge ML pipeline architecture and mentor junior engineers.
Seniority
Staff, hands-on IC with mentorship
