Apply machine learning and Python to multi-sensor infrastructure data, developing models for railway defects, anomalies, and degradation. Work across cloud and edge systems.

As Lead Data Scientist, you will analyze noisy real-world data from point clouds, radar, imagery, and satellite deformation sources. You will build statistical and AI models for infrastructure monitoring and maintenance decisions. The work combines SQL, geospatial data, experimental design, and uncertainty quantification.

Key Responsibilities:
Develop machine learning and deep learning infrastructure analysis methods
Build algorithms detecting track, subsurface, surface, and vegetation exceptions
Deploy AI models into onboard units and cloud platforms




Forecast asset degradation and remaining service life
Validate outputs against field records and regulatory thresholds

Requirements:
Degree in quantitative discipline; master's or doctorate preferred
Two or more years modeling noisy real-world data
Robust Python and SQL programming skills
Experience with sensor-derived data types
Knowledge of validation and uncertainty quantification

Lead infrastructure analytics through Python, machine learning, sensor data, and validated predictions supporting railway maintenance decisions.
J-18808-Ljbffr

📌 Machine Learning Infrastructure Data Scientist Toronto (Canada)
🏢 ApoSys Technologies
📍 Canada