Machine Learning Resident

Adam Danyleyko, Product Owner, Advanced Technology

**About the Role**

This is a paid residency that will be undertaken over a twelve-month period with the potential to be hired by our client, Carson Integrated, afterwards (note: at the discretion of the client). The resident will report to an Amii Scientist and regularly consult to and work with the Client team to share insights and engage in knowledge transfer activities.

**About our Client**

Carson Integrated is a well-respected consulting firm of natural resource management professionals who provides environmental, forestry, and GIS consulting services to clients in the Upstream Oil & Gas, Pipeline, Sand & Gravel, Electrical Utility, and Forest industries throughout Alberta. Our team advocates for our diverse client base that provides distinct opportunities, exceptional challenges, and a work environment rich in variety.

People are our greatest asset Because of this, we are committed to developing our employees by providing ongoing training opportunities and rewarding performance that exceeds expectations. Our team is made up of a group of people who are friendly and thrive in a busy (and sometimes unpredictable) work environment. Our team members are fearless and unafraid to face and overcome new challenges. Not only do we work hard, but we like to have a good time at events like our infamous annual Bocce tournament or socializing together at the end of a busy week. We provide our employees with a progressive, flexible, and collaborative work environment, encouraging an entrepreneurial approach to business coupled with the opportunity for success. At Carson Integrated, our people are part of a larger team of diverse professionals committed to excellence.

**About the Project**

The purpose of this project is to utilize machine learning (ML) to classify Predicted Stream Channels (PSC) into stream classes. The ML model will be trained using a variety of predictor datasets, including Wet Areas Mapping (WAM), soil characteristics, Alberta Vegetation Inventory (AVI), terrain, and climate data, along with extensive field-verified data collected between 2001 and 2023. This project will involve thorough data preparation, including encoding, feature scaling, class balancing, and feature engineering, to ensure the data is optimized for machine learning algorithms. Multiple ML models will be tested and refined iteratively to achieve optimal predictive performance for stream classification across the Forest Management Agreement (FMA) area.

**Required Skills / Expertise**

Are you passionate about building great solutions? Do you want to drive a high impact business? You’ll be presented with opportunities to both personally and professionally develop as you build your career. We’re looking for a talented and enthusiastic individual with a solid background in machine learning.

**Key Responsibilities**:

- Build, train, and evaluate ML models for computer vision tasks, especially image segmentation
- Prepare data for ML training
- Undertake applied research on ML techniques to address the limitations in existing models
- Collaborate with project team and stakeholders to develop MVP and client focused solutions
- Participate in regular meetings with the client, preparing presentations and reports

**Required Qualifications**:

- Completion of a Computing Science, Electrical Engineering (or a related graduate program) with a specialization in Computer Vision, MSc. or PhD
- Familiarity with GIS data
- Familiarity with advanced models such as Transformers and ViTs
- Experience using classical computer vision tools and libraries (e.g., OpenCV, Pillow)
- Proficient in developing and training deep neural network models in PyTorch and/or Keras
- Proficient in Python programming language and related ML frameworks, libraries, and toolkits
- Familiarity with Ubuntu, SSH, Git, and writing clean code.
- A positive attitude towards learning and understanding a new applied domain
- Must be legally eligible to work in Canada

**Preferred Qualifications**:

- Publication record in peer-reviewed academic conferences or relevant journals in machine learning (specifically machine vision)
- Familiarity with GIS softwares e.g. ArcGIS
- Familiarity with hydrological processes, soil science principles and environmental data

**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
- Intellectual curiosity and the desire to learn new things, techniques, and technologies

**Why You Should Apply**

Besides gaining industry experience, additional perks include:

- Work under the mentorship of an Amii Scientist for the duration of the project
- Participate in professional development activities
- Gain access to the Amii community and events
- Get paid for your work (a fair and equitable rate of pay wi