VRIFY is positioned at the forefront of the mining industry's transformation, leveraging cutting-edge AI to revolutionize mineral exploration. With a focus on AI drill targeting, VRIFY is expanding its capabilities by synthesizing vast amounts of geological information. This integration enhances the precision and efficiency of exploration strategies, offering our clients innovative solutions that depart from traditional methods.
Our mission extends beyond technological advancement. We are committed to transforming how mining companies engage with investors, aiming to foster a more transparent and accountable mining investment ecosystem. VRIFY's technology enables immersive 3D and 360° presentations that provide investors with a vivid and detailed visual context, making complex geological data accessible and engaging.
As we continue to refine our AI-driven solutions, VRIFY remains dedicated to driving innovation and excellence in the mining sector, ensuring our clients and investors are well-equipped to succeed in a rapidly evolving market.
About the Role:
As a Senior Geo Data Scientist, you will be at the forefront of developing advanced machine learning models that power our platform, transforming complex geospatial data into actionable predictions that directly inform mineral exploration decisions.
In this role, you will design, build, and scale machine learning systems and data pipelines for geospatial data, working across the full lifecycle from data ingestion and feature engineering to model development, evaluation, and deployment. You will develop and productionize models on high-dimensional spatial datasets, ensuring robust workflows, reproducibility, and performance, while integrating modern AI approaches into scalable systems.
The ideal candidate has a strong foundation in machine learning and geospatial data, with experience building production-grade models and working with large-scale spatial datasets. You bring a systems-level mindset, strong technical ownership, and a collaborative approach, and you will play a key role in shaping best practices, contributing to technical direction, and advancing how we apply machine learning to geospatial problems.
Key Responsibilities:
- Design and deploy machine learning models for geospatial applications, including deep learning architectures (e.g., Vision Transformers, GNNs) applied to high-dimensional raster and spatial datasets.
- Develop scalable data pipelines for geospatial data, including preprocessing, feature engineering, sampling strategies, and spatial cross-validation.
- Build and maintain end-to-end ML workflows, ensuring reproducibility, performance optimization, and reliable generation of actionable predictions.
- Develop custom geospatial models that capture real-world spatial patterns to improve prediction accuracy and support decision-making.
- Engineer geospatial features that reflect spatial relationships and domain-specific characteristics to enhance model performance.
- Apply and advance model interpretability techniques to understand spatial patterns and quantify feature influence in complex ML models.
- Use tools like Google Earth Engine and Hugging Face to process large-scale geospatial data and integrate modern AI models into production workflow
Required Qualifications (Must-Haves):
- BSc, MSc, or PhD in Computer Science, Engineering, Geoscience, or a related field, or equivalent practical experience
- 5+ years of experience in machine learning, data science, or software development, including production ML systems
- Strong experience with modern machine learning frameworks (e.g., PyTorch, TensorFlow, JAX, scikit-learn)
- Deep understanding of machine learning architectures (e.g., transformers, vision transformers) and approaches such as clustering and ensemble methods
- Strong programming experience in at least one high-level language (e.g., Python)
- Experience building and deploying machine learning models in production environments
- Experience working with geospatial data (e.g., raster data, satellite imagery, spatial datasets)
Nice-to-Have
- Experience applying deep learning architectures (e.g., Vision Transformers, GNNs) to geospatial problems
- Experience with geospatial tools and libraries (e.g., GeoPandas, Rasterio, GDAL, QGIS, ArcGIS)
- Experience with Google Earth Engine or similar platforms
- Experience with modern AI tooling (e.g., Hugging Face)
- Background in mineral exploration, geology, or earth sciences
What We Offer:
- Health Benefits: Extensive coverage, medical, dental, and vision plans.
- Paid Time Off (PTO): Including vacation days, sick days, personal days, public holidays plus extra time during holiday season.
- Work-Life Balance: Flexible work hours, remote work options plus option to use work space in Downtown Vancouver (free snacks & gym).
- Professional Development: Career growth program to help our team unlock their potential and advance their career.
- Performance Bonuses
- Wellness Programs: Fitness allowance, work from home allowance, mental health support.
- Retirement Plan (RRSP/DPSP)
Terms of employment:
- Full-time, Permanent, Remote work in Canada.
- Compensation - $160,000 to 170,000 CAD per year
- Completion of a background check will be required for this position.
- Must be legally entitled to work in Canada
This job description has been written to provide an accurate reflection of the current job and to include the general nature of work performed. It is not designed to contain a comprehensive detailed inventory of all duties, responsibilities, and qualifications required of the employees assigned to the job. Management reserves the right to revise the job or require that other or different tasks be performed when circumstances change.
We strive to create an environment where every employee feels valued, respected, and empowered regardless of their race, gender, age, religion, identity, or experience. We understand that unique perspectives and backgrounds bring invaluable insights and contribute to the richness of our culture and the effectiveness of our solutions. If you have a disability or any special needs that we might need to accommodate, please let us know.
