Software Engineer – Machine Learning (SDV) – Power

About the role

Valeo is seeking a Software Engineer specialized in Machine Learning for powertrain applications. You will design, train, and deploy ML models on resource‑constrained edge hardware, bridging data science and embedded software development.

Key responsibilities

• Design, train, and deploy machine‑learning models optimized for edge devices.
• Perform exploratory data analysis, statistical modeling, and visualization of complex time‑series sensor data.
• Engineer features, clean, and structure raw sensor datasets for model ingestion.
• Conduct hyper‑parameter tuning to maximize model accuracy and performance.
• Optimize model inference and runtime predictions to meet real‑time constraints on target hardware.
• Develop real‑time application logic in C/C++ while using Python for training and preprocessing.
• Apply quantization, pruning, and memory‑optimization techniques.
• Process and filter noisy sensor data using methods such as Kalman filters.
• Interface with Raspberry Pi hardware, Linux/Raspbian OS, GPIO, and SPI.
• Test, benchmark, and validate ML estimators against real hardware or high‑fidelity simulators.

Required profile

• 3+ years of experience in machine learning, edge computing, or embedded software development.
• Strong background in applied data science, statistical analysis, anomaly detection, and time‑series sensor data.
• Proven expertise in feature engineering, dataset preparation, and data‑pipeline development.
• Deep understanding of model inference optimization and low‑latency runtime behavior.

Required skills

• C, C++
• Python
• TensorFlow Lite for Microcontrollers
• Scikit‑learn
• Raspberry Pi, Linux/Raspbian
• GPIO, SPI
• Kalman filter
• Quantization (float32 to int8)
• Model pruning
• Signal processing
• Hyper‑parameter tuning
• Data science and statistical analysis
• Anomaly detection
• Time‑series analysis