Data Scientist

Responsibilities & Key Deliverables

Core Responsibilities

• Design, implement, and deploy robust AI and machine learning models focused on:
  • Predictive pricing and accurate valuation of pre-owned vehicles based on comprehensive data analysis.
  • Condition assessment of vehicles through advanced sensor data interpretation and inspection report analysis.
• Develop and maintain scalable, end-to-end ML pipelines primarily using Python, ensuring efficient data processing and model execution.
• Handle diverse automotive datasets, including structured data, unstructured textual information, and time-series sensor inputs, facilitating comprehensive model training.
• Collaborate effectively with diverse teams such as product management, data engineering, and business units to drive solutions from concept to production environments.
• Oversee continual model performance monitoring, retrain models using up-to-date data, and optimize algorithms to maintain prediction accuracy over time.
• Create and maintain interactive dashboards and visualizations to communicate analytical insights clearly to stakeholders across technical and non-technical backgrounds.
• Incorporate best practices in MLOps, including model versioning, automated testing, and deployment using containerization technologies.

Essential Skills

• Proficiency in Python programming with solid experience in machine learning frameworks and libraries, such as scikit-learn, XGBoost, CatBoost, TensorFlow, and PyTorch.
• Strong command over data processing and visualization libraries including Pandas, NumPy, Matplotlib, and Seaborn to handle complex datasets and present insights.
• Hands-on experience deploying machine learning models using modern tools such as Docker, FastAPI, and MLflow to ensure seamless integration and scalability.
• Familiarity with cloud computing platforms, including AWS, GCP, or Azure, coupled with a solid understanding of MLOps workflows and automation.
• Expertise in data preprocessing, feature selection and engineering, as well as rigorous model evaluation techniques.
• Demonstrated capability to take full ownership of projects, working independently while driving collaboration with cross-functional teams.