Data Scientist & AI Engineer
Fes, Fez-Meknès, Morocco
ALTEN
Leader in Engineering and IT Services, ALTEN supports its customers’ development strategies in the areas of innovation, R&D and technological information systems.Company Description
ALTEN DELIVERY CENTER MAROC, Filiale du leader mondial de l’ingénierie et du conseil en technologie créé en 2008 et présent à Fès, Rabat, Tétouan et Casablanca, compte aujourd’hui plus de 2300 consultants et vise un centre d’excellence de 3100 consultants ALTENiens en fin 2027. Avec plus de 90 recrutements par mois, ALTEN Maroc est désormais un acteur majeur de l’insertion professionnelle des ingénieurs. Nous accompagnons nos clients, leaders de l’Industrie dans leurs stratégies de développement dans les domaines de l’automobile, du ferroviaire, de l’IT, de la R&D et des Télécoms & Médias.
Job Description
Design, develop, and train an AI model based on historical data from automotive thermal validation tests to predict key performance indicators (KPIs) for future vehicle lines. The ultimate goal is to reduce or eliminate physical testing, accelerate time-to-market, and optimize resource allocation
Main Responsibilities:
- Data Collection & Processing:
- Gather, clean, and structure historical test data from thermal validation campaigns (e.g., climatic chamber tests, endurance tests).
- Ensure data consistency and quality from multiple sources (physical tests, benches, in-vehicle sensors, etc.).
- AI / ML Model Development:
- Define the architecture of an AI model (e.g., deep learning, machine learning, hybrid models) dedicated to KPI prediction.
- Train the model using historical datasets, including:
- Coolant circuits (battery, e-motor, HVAC, heat losses)
- Refrigerant circuits (pressure drop, IHX)
- Component thermal behavior (battery cells, power electronics, cabin, etc.)
- Heat exchangers, pumps, valves, actuators
- Interaction with ambient conditions and driving cycles
- Analysis & KPI Prediction:
- Identify correlations between physical parameters and the target KPIs.
- Generate predictions for new vehicle lines with no physical validation.
- Benchmark AI predictions against historical physical test results to validate the model.
- Documentation & Reporting:
- Document the modeling process, assumptions, and results.
- Present findings and recommendations to key stakeholders (validation teams, design teams, quality, management).
Qualifications
Education:
- Master’s degree (or equivalent) in:
- Data Science / Artificial Intelligence
- Mechanical / Thermal / Energy Engineering
- Automotive or Embedded Systems Engineering
Experience:
- More than 1 year of experience in data science or AI applied to complex technical systems.
- Experience in the automotive sector or thermal validation is a strong advantage.
Technical Skills:
- Data Science & AI:
- Proficiency in Python (Pandas, Scikit-learn, TensorFlow or PyTorch)
- Knowledge of regression, neural networks, supervised learning models
- Experience with time-series data and predictive modeling
- Automotive Thermal Systems:
- Understanding of vehicle thermal systems (cooling loops, HVAC, electrified components)
- Familiarity with physical testing procedures and KPIs related to thermal performance
- Other Tools:
- Data visualization tools (Matplotlib, Plotly, Power BI, etc.)
- Ability to communicate and document technical work in English and French
- Strong analytical mindset and autonomy
Soft Skills:
- Technological curiosity and innovation mindset
- Team player with the ability to collaborate across functions (data science, validation, design, calibration)
- Strong problem-solving and critical thinking skills
- Results-oriented with a focus on optimization and efficiency
* Salary range is an estimate based on our AI, ML, Data Science Salary Index 💰
Tags: Architecture Data visualization Deep Learning Engineering KPIs Machine Learning Matplotlib ML models Pandas Plotly Power BI Predictive modeling Python PyTorch R R&D Scikit-learn TensorFlow Testing
More jobs like this
Explore more career opportunities
Find even more open roles below ordered by popularity of job title or skills/products/technologies used.