“If you are interested in applying machine learning to real-world industrial challenges, specifically in predictive maintenance using time-series sensor data - this is a perfect opportunity for you. Be a part of a team of research and machine learning scientists developing models to predict equipment failures and optimize maintenance strategies, and get mentored by some of the best minds in AI while doing it.”

• Dave Staszak, Lead Machine Learning Scientist

REQUIRED SKILLS / EXPERTISE

We’re looking for a talented and enthusiastic individual with solid knowledge of machine learning, demonstrated experience with supervised learning, and experience in applied settings.

REQUIRED QUALIFICATIONS:

• Completion of a graduate level program or higher (M.Sc/Ph.D) in Computing Science, ML or Engineering
• Research or project experience in time series analysis, anomaly detection, and predictive maintenance use cases
• Proficient in Python programming language and related ML frameworks, libraries, and toolkits (e.g., Scikit-learn, TensorFlow, PyTorch, Pandas)
• A positive attitude towards learning and understanding a new applied domain
• Must be legally eligible to work in Canada

PREFERRED QUALIFICATIONS:

• Previous experience applying machine learning to time series data for predictive maintenance problems
• Experience with ARIMA, LSTM, matrix profiling, and autoencoders
• Familiarity with sensor data characteristics and challenges
• Experience with deploying machine learning models in production environments or strong software engineering (or MLE) skills is a plus

NON-TECHNICAL REQUIREMENTS:

• Desire to take ownership of a problem and demonstrated leadership skills
• Interdisciplinary team player enthusiastic about working together to achieve excellence
• Capable of critical and independent thought
• Able to communicate technical concepts clearly and advise on the application of machine intelligence
• Intellectual curiosity and the desire to learn new things, techniques, and technologies

ABOUT THE ROLE

This is a paid Residency that will be undertaken over an eight-month period with the potential to be hired by our client afterwards (note: at the discretion of the client). The Resident will be reporting to an Amii Scientist and regularly consult with the Client team to share insights and engage in knowledge transfer activities.

WHAT YOU WILL BE DOING

In this role, you will be instrumental in developing machine learning models for predictive maintenance of Supreme International’s feed processing equipment. Your work will focus on analyzing time-series sensor data to detect anomalies and predict potential failures. You will explore and implement both supervised and unsupervised learning techniques, and various classification models. You will be responsible for data preprocessing, including handling missing data, noise reduction, and synchronization issues. You will also contribute to the development of strategies for failure labeling and defining appropriate time windows for model training and prediction. You will collaborate with interdisciplinary teams, participate in project meetings, and contribute to reports on model performance and project milestones. Your efforts will directly contribute to shifting Supreme International from a reactive to a proactive maintenance strategy, reducing downtime, optimizing maintenance schedules, and enhancing overall operational efficiency.

KEY RESPONSIBILITIES:

• Design, implement, optimize, and evaluate time series machine learning models tailored for predictive maintenance and anomaly detection, with a specific focus on developing, training, and refining solutions for analyzing sensor data from feed processing equipment.
• Prepare and curate high-quality, time series datasets for model training and validation from diverse sources.
• Utilize state-of-the-art machine learning frameworks and tools, including TensorFlow, PyTorch, Scikit-learn, and Pandas, to enhance model performance and streamline data processing.
• Collaborate with cross-functional teams to build and deploy predictive maintenance solutions that address client needs, ensuring seamless integration into existing systems.
• Engage in regular client meetings, contributing insights and updates on model performance and project milestones through presentations and detailed reports.
• Optimize machine learning pipelines to ensure efficient and scalable time series analysis and anomaly detection capabilities, leveraging techniques like ARIMA, LSTM, and matrix profiling.