Matching Engine for Environmental Solutions - BC-960

Project type: Innovation
Desired discipline(s): Computer science, Mathematical Sciences, Operations research, Statistics / Actuarial sciences
Company: XG Energy LTD.
Project Length: 6 months to 1 year
Preferred start date: As soon as possible.
Language requirement: English
Location(s): BC, Canada
No. of positions: 1
Desired education level: Master'sPhD
Open to applicants registered at an institution outside of Canada: No

About the company: 

XG Energy is a startup based in Vancouver, Canada, is building a platform that connects environmental solutions with the specific challenges they are designed to address.

XG Energy’s customers include researchers, companies seeking sustainable solutions, investors focused on ESG goals, and organizations working to solve environmental challenges.

XG Energy solves the challenge of connecting environmental innovations with real-world problems by bridging the gap between researchers, companies, and sustainability goals.

The platform is designed to:

● Link environmental solutions directly to real-world environmental challenges.

● Match companies needing to meet ESG goals with researchers working on sustainability projects.

● Connect companies seeking sustainable products with the innovators who create them.

By connecting these three points, XG Energy helps researchers not only fund their solutions but also implement them, either by addressing real environmental problems or by matching them with companies actively seeking sustainable innovations. The platform uses an AI-driven matching algorithm that analyzes project summaries and environmental needs to create high-quality, actionable connections. The platform also includes an interactive map that displays environmental challenges, solutions, and institutions worldwide, allowing users to easily find opportunities for collaboration and impact.

Describe the project.: 

XG Energy is building the first AI-powered platform that connects real-world environmental challenges such as wildfires, carbon emissions, and water pollution with the research, technologies, and solutions designed to address them. The platform uses a custom-built algorithm to match environmental problem profiles with compatible sustainability-focused projects, researchers, and solution providers.
This project focuses on refining and optimizing the AI matching engine at the heart of the MVP. The selected researcher will work with XG’s technical and strategy team to improve how solution and problem data are classified, scored, and matched.
Key tasks include evaluating and optimizing the current matching algorithm, improving relevance scoring models, and suggesting new ways to classify and rank projects based on inputs such as SDG alignment, ESG impact areas, environmental indicators, and geographic relevance. Tasks may also involve integrating NLP techniques to better interpret project summaries and structuring metadata to improve algorithmic performance. The researcher will help identify which models are most effective based on limited, structured, and semi-structured data.
The final goal is to produce a scalable, interpretable, and high-accuracy recommendation system that powers the MVP version of the platform. This will help ensure that researchers and solution providers are meaningfully matched with the problems they are best suited to solve, supporting faster innovation and more targeted climate impact.
This role is ideal for a Master’s, PhD, or Postdoc in computer science, statistics, or data science who is passionate about using AI for social and environmental good.

Required expertise/skills: 

The ideal candidate will have a background in computer science, data science, statistics, or a related field, ideally at the Master’s, PhD, or Postdoctoral level. Experience with machine learning, recommendation systems, or information retrieval is highly relevant to this project.
Useful skills may include:
● Proficiency in Python and libraries such as scikit-learn, pandas, NumPy, or similar
● Familiarity with NLP tools (e.g., spaCy, NLTK, or transformers) to analyze project summaries
● Experience with relevance scoring models, classification techniques, or ranking algorithms
● Understanding of how to work with structured and semi-structured data
● Ability to test, compare, and validate different models and approaches based on real-world performance
Assets (optional):
● Experience with recommender systems or semantic similarity models
● Familiarity with SDG/ESG frameworks or sustainability-related datasets
● Knowledge of cloud-based tools (e.g., Google Colab, AWS, or similar)
● Strong communication skills to collaborate with a multidisciplinary team
The candidate doesn’t need deep domain knowledge in sustainability but should be interested in applying data science to real-world environmental and social impact.