The posting
Job Informationen ######
Location: Zurich Workload: Full-time Start: By agreement Your tasks: You build ML models that predict residual sensor error from observable signals such as temperature, thermal gradients, quadrature amplitude, drive signals and sensor diagnostics. You define rigorous validation protocols across unseen thermal profiles and physical sensor units to demonstrate genuine generalisation. You benchmark learned approaches against a tuned classical baseline combining per-unit thermal compensation and adaptive Kalman filtering. You quantify the observability boundary and identify which errors are predictable and which are not. You train and evaluate models offline on sensor characterisation data, separating meaningful physical correlations from artefacts and overfitting. You work with FPGA and DSP engineers to translate successful approaches into lightweight models for low-latency embedded deployment. You communicate results clearly, including when the evidence shows a classical approach remains the better solution. Your profile: BSc, MSc or PhD in computer science, applied mathematics, applied physics, machine learning or a related technical field Strong applied machine learning experience with time-series, regression, sensor or instrumentation data Strong Python or MATLAB skills and experience with PyTorch, scikit-learn or equivalent frameworks Experience with modest, high-value datasets where validation strategy and data quality matter as much as model architecture Strong understanding of model validation, generalisation, overfitting, feature engineering and experimental design Enough physics and signal-processing knowledge to judge whether a discovered relationship is physically meaningful C/C++ skills highly desirable Advantageous: sensor calibration, metrology, inertial sensing, embedded ML deployment, aerospace, defence or robotics experience
Benötigte Skills ######
- Python
- Machine Learning
- Matlab
- C
- C++
- Embedded
- Bachelor
- Master
