DTICI Data Scientist T8

Become part of our team!   Team introduction Department of  Data and Analytics has its hub at DTICI Bengaluru India catering to data and analytics requirements for Daimler Truck. we are 150+ strong team comprising of Data engineers, Data scientists, AI engineers and Analysts What makes the team/department special? Highly energetic and young team that solves business problems that have the potential to define we build our trucks   

Job Title: Data Scientist (Iterative Model Development – Traditional ML)

Job Summary: We are seeking a Data Scientist with expertise in building and optimizing traditional ML models, specifically within the automobile domain. The ideal candidate will have strong experience in classical ML algorithms, survival models, time series, statistical modelling, and deployment of predictive models. Experience with streaming data and telematics data solutions is highly desirable.

Key Responsibilities:

• Work with Daimler’s Businesses and Enabling Areas to support key business functions
• Contribute to storyboarding our results, support recommendations for an executive-level audience and produce leadership-quality deliverables
• Develop and optimize traditional ML models (regression, decision trees, SVM, XGBoost, etc.) with strong knowledge on Hypothesis testing.
• Perform feature engineering and dataset preprocessing for model training.
• Build scalable machine learning pipelines for real-world applications.
• Work on time series forecasting, anomaly detection, recommendation systems, etc.
• Optimize model performance using hyperparameter tuning and cross-validation.
• Deploy ML models into production using cloud and on-premises solutions.
• Collaborate with cross-functional teams to integrate ML models into business processes.
• Analyze and interpret telematics data to derive actionable insights.
• Develop solutions for streaming data processing and real-time analytics.

• Good Communication  & presentation skills.
• Strong Knowledge of Azure Components Azure Data Lake, Azure Data Factory, Azure SQL, Azure Databricks
• Master in Statistics/Machine Learning/Economics/ Big Data analytics (Full -Time)
• Strong experience in object-oriented programming using Python & PySpark
• Experience developing, training, and evaluating (supervised/unsupervised) machine learning models such as linear regression, Logistic regression, k-means, time series forecasting, Hypothesis testing (ANOVA, t-test, etc.), random forest, SVMs, Naive Bayes, gradient boosting, kNN, Deep learning algorithms like CNN, ANN and Reinforcement learning, Anomaly detection
• Familiar with statistical distributions, correlation analysis, descriptive statistics, ROC, F1-Score, etc.
• Proficiency in Python, Scikit-learn and ML libraries.
• Strong understanding of statistical modeling and data preprocessing.
• Should have had at least 2 to 3 use cases where the candidate would have gained the experience of end to end development of Data science solution and deployment
  • Problem definition - white boarding
  • Hypothesis building and testing and Exploratory data analysis
  • Data engineering to curate data for model Training, testing, deployment and MLops