Senior Machine Learning Engineer - Power Factors
Remote · Montréal, Quebec, Canada
Job Summary
Senior Machine Learning Engineer to own architecture decisions for PF's time-series foundational model, design tokenization for multi-modal training corpora, and scale from PoC to production across a ~1,000-site fleet. Role involves building/maintaining containerized training environments, optimizing distributed training pipelines, managing a model registry, and ensuring alignment of model outputs with business use cases. Collaboration spans Backend/Data Engineering, Tech Lead, and Product teams; responsibilities include data quality handling for sensors, multi-frequency and multi-modal signals, curriculum and masking strategies for pre-training, and documenting runbooks and architecture decisions. Must-have background in time-series modelling, transformer/sequence architectures, and strong Python/PyTorch skills; beneficial familiarity with chronos-like models, uncertainty quantification, scalability for large fleets, and experience in renewable energy/industrial IoT domains.
Required Qualifications
- 5+ years of ML engineering experience
- Deep expertise in time-series modelling (multivariate, multi-frequency, heterogeneous sensor data)
- Proven ability to design and train transformer-based or sequence model architectures from scratch
- Distributed training engineering (GPU cluster config, mixed-precision, gradient accumulation, checkpointing, fault recovery)
- Strong Python and PyTorch (or JAX); familiarity with HuggingFace ecosystem
- MLOps fluency: experiment tracking, model registry design, reproducible pipelines, automated retraining
- Excellent written and verbal English communication skills
Apply with one swipe on Sorce. We auto-fill applications and apply on your behalf — no cover letters, no 40-minute forms.
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.