Your team and your responsibilities
We are looking for an AI Explainability Engineer for our team at TME whose work will enhance driver safety and comfort. The candidate will design, develop, and assess XAI systems that focus on monitoring and real-time assessment of driver distractions and the cognitive load and mental workload of the driving environment.
This is a fixed-term position of 16 months.
Your responsibilities
1. Develop and implement concepts and systems for explainability of AI systems aimed at automotive applications.
2. Augment the existing AI models on detection, interpretation, and explanation of driver distraction, mental workload, and cognitive load.
3. Design and refine systems for real-time monitoring and evaluation of driver behavior in varying driving environments.
4. Diagnose and assess the parameters contributing to driver distraction and cognitive load, and provide mechanisms for their mitigation.
5. Develop, design, and operationalize frameworks for validation to track, evaluate, and provide transparency and accountability on the trust and AI model bias.
6. Work with other team members, like human factors specialists and engineers and designers, to implement systems for driver-assistance technologies.
7. Participate in the preparation of scientific and technical documents, as well as the internal dissemination of knowledge on automotive explainable AI.
Your Profile
8. You are fluent in English (TME’s business language)
9. Master’s or PhD in Computer Science, Artificial Intelligence, Machine Learning, Cognitive Science, or a related field.
10. Experience with explainable AI (XAI), interpretable models, and human-centered AI systems applicant is required to have AI knowledge.
11. Have a working history with machine learning, deep learning, or cognitive modeling.
12. Experience working with real-time data streams and data streams and behavioral monitoring, (with priority in automotive or human factors streams).
13. High level of fluency in at least one of the following programming languages: Python, and C++, as well as working knowledge of a least one of the following ML frameworks: TensorFlow, PyTorch, etc.
14. Awareness of validation methods, operational metrics of models, and safety-critical systems.
A truly diverse, equitable and inclusive workplace