Senior Applied Scientist, ML Predictive Maintenance (Asset Intelligence)

Design, develop and optimize machine learning models for fault detection and classification end-to-end e.g. data and training modeling choices to evaluation strategies and production constraints.

Perform EDA on vibration, OT and time-series data to uncover insights and identify patterns indicative of faults or anomalies.

Conduct experiments and evaluation of various algorithms on time-series modeling, signal processing, and statistical methods, to optimize model performance.

Partner with PMs in product feature discovery and roadmap prioritization through validating product hypotheses, designing success metrics and quantifying end user impact

Collaborate with domain experts to validate findings and ensure alignment with real-world applications.

Engage with your community of peers to challenge the status quo, improve our shared ways of working, and influence overall architecture decisions, continuing to foster our culture of Applied Science excellence

On-call duties

Master’s or Ph.D. in Computer Science, Data Science, Mechanical Engineering, Electrical Engineering, or a related field with a focus on condition monitoring or machine learning applications.

5+ years of proven programming skills using standard ML tools such as Python, PyTorch, Tensorflow etc.

Strong foundational knowledge in machine learning, data science, and statistics

Familiarity with time-series modeling techniques and feature engineering.

Ability to deliver production-grade code that is well-tested, maintainable, and evaluated through rigorous experimentation.

An expert level of English, both spoken and written, is required, as the individual will need to lead platform engineering managers across multiple teams, present technical priorities to executive stakeholders, and align with engineering leaders outside Québec on a daily basis.