Aaron L. looks like a good fit?
We can organize an interview with Aldin or any of our 25,000 available candidates within 48 hours. How would you like to proceed?
Schedule Interview NowAaron L. AI, Python and General Development
My name is Aaron L. and I have over 1 years of experience in the tech industry. I specialize in the following technologies: Artificial Intelligence, Industrial Automation, SCADA, Optimization Modeling, C++, etc.. I hold a degree in Master of Science (MS), Bachelor's degree. Some of the notable projects I’ve worked on include: Acoustic Event Dector, Rogue7 Pump Optimizer. I am based in Edmonton, Canada. I've successfully completed 2 projects while developing at Softaims.
I am a business-driven professional; my technical decisions are consistently guided by the principle of maximizing business value and achieving measurable ROI for the client. I view technical expertise as a tool for creating competitive advantages and solving commercial problems, not just as a technical exercise.
I actively participate in defining key performance indicators (KPIs) and ensuring that the features I build directly contribute to improving those metrics. My commitment to Softaims is to deliver solutions that are not only technically excellent but also strategically impactful.
I maintain a strong focus on the end-goal: delivering a product that solves a genuine market need. I am committed to a development cycle that is fast, focused, and aligned with the ultimate success of the client's business.
Main technologies
AI, Python and General Development
1 year
Artificial Intelligence
1 Year
Industrial Automation
1 Year
SCADA
1 Year
Additional skills
- Artificial Intelligence
- Industrial Automation
- SCADA
- Optimization Modeling
- C++
- Python
- TensorFlow
- Docker
- JavaScript
- GIS
- REST API
- Rust
- Machine Learning
- Full-Stack Development
- Data Analytics
- Fullstack
Direct hire
Potentially possible
Previous Company
IBM Canada
Experience Highlights
Acoustic Event Dector
We performed a pilot project to identify leaks in water networks through analysis of sound files from acoustic loggers. We had some success classifying the sound files directly but our big breakthrough was the development of a new technique for analyzing the data. Whereas traditional acoustic leak detection looks at acoustic recordings as a snapshot in time, trying to decide if the currently recorded sound is a leak, we decided to evaluate them in the context of the long term behaviour of the logger. This new approach allowed us to not only catch all previously known leaks, but also detect new leaks that were previously below the detection threshold, track the progression of leaks as they grew larger, and detect other tricky conditions like detached loggers. NOTE: The screen shots here depict the city of Victoria but that's only because Victoria has a publicly available set of GIS data. The actual data came from a water utility in another country and was relocated to Victoria for display purposes.
Rogue7 Pump Optimizer
I am the author and main developer for one of our core products, the Rogue7 Pump Optimizer. In the US, pumping drinking water and wastewater accounts for 3-4% of total US energy use and emits around 45 million tons of greenhouse gases (GHG). The Rogue7 Pump Optimizer helps to address this problem by creating optimized pump schedules for Municipal Water Networks. The optimized schedules it creates can help operators to minimize energy use, greenhouse gas emissions, and costs, while satisfying all safety and operational constraints. The core of our approach involves building ML models that predict key network metrics such as energy usage, tank levels, key pressures, and other operationally relevant metric. These ML models can then be leveraged through numerical optimization techniques to develop optimized schedules. Gathering the data to build these ML models is a key challenge. When available, a SCADA system with a good historian can provide sufficient data to build predictive models (an approach we've used with other pump systems). Large pump systems also often have existing hydraulic simulation models, which run much more quickly than real time (though still too slow for direct optimization). But these simulation models can be used to gather the data used to build our initial set of predictive models before we start gathering our own data from the live system. The product is still awaiting its first full scale pilot but we are in the process of performing a proof-of-concept project with a UK water utility.
Education
University of Alberta
Master of Science (MS) in
2009-01-01-2014-01-01
University of Alberta
Bachelor's degree in
2001-01-01-2006-01-01
Languages
- English
Github