The Data Scientist will work within the Global Data & AI organization supporting Daimler Truck’s Electrification and Quality Engineering functions. The role focuses on applying machine learning, statistical modeling, and signal analysis to battery data from test benches, field vehicles, telematics systems, and BMS (Battery Management System) logs.
The primary objective is to detect early signs of degradation, thermal instability, SOH/SOC inconsistencies, charging anomalies, and performance drifts. The role includes developing classical AI/ML models, conducting feature engineering for time-series sensor data, creating diagnostic dashboards, and contributing to predictive maintenance solutions for battery systems.
This position is ideal for candidates with 1–3 years of experience and a strong interest in automotive electrification and battery analytics.
Battery Analytics & Modeling
- Build classical ML models (Random Forests, SVMs, Gradient Boosting, clustering algorithms) for detecting battery anomalies and predicting degradation.
- Analyze BMS data such as:
- Voltage/Current curves
- Temperature gradients
- Charging/discharging cycles
- SOC/SOH trends
- Cell balancing behavior
- Develop time-series models for early detection of:
- Fast‑rising temperatures
- Unstable cell voltages
- Internal resistance changes
- Charging anomalies & slow charging patterns
Data Engineering & Feature Development
- Perform statistical analysis and feature engineering on battery sensor data.
- Work with data engineers to ingest and process large telematics/battery datasets.
- Develop derived KPIs such as capacity fade, thermal runaway indicators, cycle‑life predictors, etc.
- Collaborate on data pipelines using Python, SQL, Azure Data Factory, or similar tools.
Model Deployment & Collaboration
- Support deployment of models into cloud or on‑prem execution environments.
- Work with Quality SMEs, Battery System Engineers, and Vehicle Testing teams.
- Build explainability artifacts and present findings through dashboards (Power BI/Plotly).
Research & Optimization
- Benchmark battery behavior across vehicle models, climatic conditions, and duty cycles.
- Conduct root-cause analysis using clustering, PCA, or anomaly scoring.
- Contribute to documentation, model versioning, and continuous improvement processes.
Technical Skills
- Bachelor’s/Master’s degree in Data Science, Computer Science, Electrical Engineering, Mechatronics, or related disciplines.
- 1–3 years of experience in:
- Classical ML algorithms (Regression, SVMs, Decision Trees, Clustering, Time-series ML)
- Python for data science: NumPy, Pandas, SciPy, Scikit-learn
- Signal processing or time-series analysis
- Basic MLOps practices and model packaging
- Good understanding of:
- Data cleaning, outlier detection, exploratory data analysis
- Feature selection and feature engineering
Automotive/Battery Domain Skills (Preferred)
- Understanding of:
- Lithium-ion cell behavior
- Battery charging/discharging curves
- Thermal behavior of cells
- SOC/SOH estimation methods
- BMS signals and diagnostic trouble codes
- Exposure to working with:
- CAN data, telematics data, or test bench logs
- Battery test cycles (CCC, HPPC, drive cycles, etc.)
Tools & Platforms
- Python, Jupyter, Git
- SQL, Azure ML, Azure Databricks (or similar platforms)
- Power BI/Tableau for visualization
- Bonus: Familiarity with MATLAB for battery modeling
Soft Skills
- Strong problem‑solving and data interpretation abilities.
- Curiosity and willingness to explore battery behavior and EV analytics.
- Ability to communicate insights to engineering stakeholders.
- Collaborative mindset for working with mechanical, electrical, and software teams.
