We are looking for a highly skilled Data Scientist with 6+ years of experience in handling large-scale realworld datasets—particularly from autonomous fleets, commercial trucks, or connected vehicles. The ideal candidate will have strong analytical, modeling, and machine learning capabilities and will help us unlock actionable insights from multi-modal data collected through our vehicles.
Roles and Responsibilities
• Analyze massive amounts of sensor and telemetry data (GPS, CAN, LiDAR, camera, IMU, radar) from truck fleets.
• Develop machine learning and statistical models to detect anomalies, optimize routing, predict failures, and assess driver behaviour.
• Collaborate with cross-functional engineering teams to improve autonomy performance and operational intelligence.
• Build pipelines to clean, process, and transform structured and unstructured vehicle data.
• Apply time-series analysis, predictive modeling, and clustering techniques on driving patterns and truck dynamics.
• Create intuitive dashboards and tools to visualize large-scale vehicle and behavioural datasets for business and product teams.
• Translate findings into actionable insights to improve autonomy algorithms and fleet operations.
Required Skills and Qualifications
• Bachelor's or Master’s degree in Computer Science, Data Science, Statistics, or related field.
• Minimum 6 years of hands-on experience in data science and analytics.
• Strong programming skills in Python and experience with libraries like Pandas, NumPy, Scikitlearn, TensorFlow/PyTorch.
• Experience with big data tools like Spark, AWS/GCP data pipelines, or similar platforms.
• Deep understanding of time-series data, signal processing, and ML for spatiotemporal datasets.
• Experience working with connected vehicle data or telemetry from trucks/autonomous systems is highly preferred.
• Familiarity with vehicle dynamics, CAN data decoding, or driver behaviour modeling is a plus.
• Proficiency in SQL, data visualization tools (Tableau, PowerBI, Plotly, etc.).
Preferred Skills
• Familiarity with deep learning frameworks (PyTorch, TensorFlow).
• Experience in working with time-series or geospatial data.
• Exposure to big data tools (Spark, Hadoop) and NoSQL databases.
• Knowledge of version control, Docker, and CI/CD pipelines.
• Background in autonomous systems, IoT, or mobility data is a plus. Good To Have.
• Experience working in mobility, logistics, or automotive analytics.
• Knowledge of autonomous driving stack or sensor fusion concepts.
• Exposure to edge AI deployments or model compression techniques.
Python, Pandas, NumPy, Scikit-learn, TensorFlow, PyTorch, Spark, AWS, GCP, SQL, Tableau, PowerBI, Plotly, Hadoop, NoSQL, Docker, CI/CD, Time-series analysis, Signal processing, Machine learning, Statistical modeling, Anomaly detection, Predictive modeling, Clustering, Data visualization, Geospatial data, Spatiotemporal datasets, vehicle dynamics, CAN data decoding, Driver behaviour modeling, Sensor fusion, Edge AI, Model compression, Version control, IoT, Mobility data, Autonomous systems, Autonomous driving stack, Data pipelines.