Lead Machine Learning Engineer
- Markham, ON
- Permanent
- Full-time
- Lead the design, development, and deployment of scalable, high-performant, maintainable, accurate and reliable ML and generative AI models for grid innovation applications within Grid Automation.
- Develop AI/ML applications for customer-driven use cases, including predictive maintenance, anomaly detection, failure analysis, optimized control and forecasting, as well as business efficiency.
- Monitor, maintain, and optimize deployed AI/ML models to continuously enhance their accuracy and performance.
- Support the design, building and maintenance of MLOps pipelines in collaboration with team Architects, MLOps Engineers and other partners.
- Embrace MLOps principles to streamline the deployment and updating of ML models in production.
- Validate and verify AI/ML proof-of-concepts in real-world environments, ensuring they meet the diverse needs of our customers.
- Manage the collection, structuring, and analysis of data to enable seamless AI/ML applications.
- Ensure that models are production-ready and continuously improve/evolve in line with emerging needs and technologies.
- Collaborate closely with cross-functional teams to identify business challenges and deliver AI-driven solutions that are efficient, accurate, reliable, maintainable and scalable.
- Integrate AI/ML solutions effortlessly into grid automation systems, whether in the cloud or at the edge.
- Master’s or PhD in Computer Science, Information Technology, Electrical Engineering, or a related field.
- Excellent foundation in AI/ML techniques, including supervised, unsupervised, and reinforcement learning, deep learning, and large language models (LLMs).
- Experience with ML frameworks such as TensorFlow, PyTorch, and scikit-learn.
- Proficiency in programming languages such as Python, R, MATLAB, C# or C++.
- Proven experience in applying AI/ML frameworks/workflows, AI/MLOps and CI/CD using cloud-native and on-prem development and deployment in OT/industrial automation environments.
- Hands-on, demonstrable experience deploying ML models in production environments using MLOps principles.
- Proven experience in the energy, smart infrastructure, or industrial automation sectors, with expertise in system protection, automation, monitoring, and diagnostics.
- Experience with time-series analysis, signal processing, load forecasting, optimization and predictive maintenance relevant to energy systems and grid operations.
- Familiarity with cloud platforms (AWS, Azure, Google Cloud) and microservices architecture.
- Familiarity with GraphDB, MongoDB, SQL/NoSQL, and other DBMS technologies.
- Excellent communication, organizational, documentation and problem-solving skills.
- Strong emphasis on teamwork, having a can-do attitude, problem solving, positivity, collaboration, and fostering inclusive environments.
- Ability to multi-task in a fast-paced, multi-task rich environment.
- Experience with data modeling, containerization (Docker, Kubernetes), and distributed computing (Spark, Scala).
- Understanding of system automation, protection, and diagnostics for power utilities and industrial customers.
- Experience with deep learning algorithms, reinforcement learning, NLP, and computer vision in applicable domains.