AI/ML Expert – Driver Modeling (Computer Vision)

About the role

We are seeking a highly skilled AI/ML Researcher to design, develop, and deploy cutting‑edge computer vision systems for driver modeling applications, enhancing safety, comfort and personalization of next‑generation automotive interior monitoring products.

Key responsibilities

• Conduct pioneering research to develop novel algorithms and models for driver modeling tasks.
• Develop domain‑aware representation learning from multi‑modal sensor data, extracting robust and interpretable features.
• Advanced detection of driver distraction, drowsiness, micro‑sleeps, sleep onset, and emotional states using statistical and probabilistic methods.
• Interpret driver intent, head pose, gaze, eye‑gaze estimation, and recognize specific activities such as phone usage or interaction with vehicle controls.
• Understand 3D interior scene and driver‑vehicle interactions for holistic cabin perception.
• Design, train, and optimize deep learning models (CNNs, Transformers, RNNs) and traditional computer‑vision algorithms for real‑time embedded automotive systems.
• Devise data collection, annotation, and augmentation pipelines for large‑scale automotive datasets.
• Stay current with AI/ML research and contribute to patents or publications.

Required profile

• Master's or PhD in AI/ML, Computer Science, Electrical Engineering, or related field.
• Strong programming skills in Python and C++ with performance optimization experience.
• Proven expertise in computer‑vision fundamentals, both traditional techniques and deep‑learning frameworks.
• Hands‑on experience building, training, and deploying perception systems for driver modeling or related automotive interior sensing.
• Solid grasp of mathematical, statistical, and information‑theory concepts (linear algebra, calculus, probability, entropy, etc.).
• Excellent analytical and problem‑solving abilities for safety‑critical automotive systems.

Required skills

• Python
• C++
• PyTorch
• TensorFlow
• CNN, Transformers, Recurrent Neural Networks
• Computer‑vision algorithms, feature descriptors, optical flow
• Multi‑modal sensor fusion (RGB, IR, depth, radar)
• Model compression, quantization, deployment on embedded automotive hardware
• Real‑time performance optimization