EMAGIN provides water and wastewater utilities with an Artificial-Intelligence driven platform to help their staff make smarter operational decisions in real-time when controlling their critical infrastructure. In doing so, we’re able to help utilities drive down their operational costs, enhance reliability of services and reduce risks to public safety and the environment.
The Right Candidate:
In short we’re looking for impact-minded data scientists and engineers – those who are passionate about making the world a better place through the use of AI and machine learning. The right person for this role will enjoy diving into large, messy time-series datasets, designing robust predictive models, and developing scalable algorithms for real-time data ingestion.
The Data Scientist will engage with a team of modellers, engineers, and project managers to mine water, energy and chemical data; as part of EMAGIN’s Hybrid Adaptive Real-time Intelligence (HARVI) platform. Core responsibilities include:
- Design and implementation of supervised algorithms that learn complex system dynamics from live datasets
- Design and development of algorithms to enhance EMAGIN’s real-time data ingestion engine (requires wrangling large datasets from over 20,000 data sources)
- Practice rigorous statistical error analysis and model validation techniques to verify structural and predictive integrity of models
- Dive into data, clean it up, and pull out insights that can be used to improve model performance
- Contribute to the technical vision of EMAGIN
Why we think you will love working with us:
- Be a part of building something that will make a difference in the world
- Have a big impact at an early-stage, VC-backed software startup
- Work with a small team of experienced entrepreneurs creating socially-mindful technology
Skills & Requirements:
- Degree in Computer Science, Statistics & Applied Math, Systems Design Engineering or similar field. Masters or PhD degree is an asset.
- Solid Python developer (Tensorflow, Scikit learn, Numpy, Pandas, Scipy, Sympy, Statsmodels etc.)
- Experience working with large amounts of data (preferably time series) in NoSQL/SQL in conjunction with high performance computing like Spark, Hadoop, Hive, MPI or any other open source library
- Excellent understanding of time-series regression and classification; experience with ensemble techniques and rigorous model building and validation processes
- Bonus points for published international research papers, experience/interest in process control and automation
- Authorized to work in Canada (onsite in our Kitchener office)
If this sounds challenging and interesting enough, and you have prior experience or expertise in any of these related fields, get in touch! Please apply with your résumé/CV and any links/attachments about relevant projects and related work.