Geologist - Spatial AI Data & Feature Architect

4Point AI (Techstars '24); Canada; On-site; CAD 90,000 - 120,000; Full time

Benefits offered by this job

Competitive compensation

Opportunity to work in Spatial AI for矿

Job summary

4Point AI in Canada seeks a Geologist to advance geological data and feature development for machine‑learning models. You will gather drillholes, assays, maps, geophysics, remote sensing, and public datasets while preserving geology, source, resolution, and uncertainty.

You will translate alteration patterns and structural settings into new measurable representations, and develop prototypes with the ML team, documenting requirements, methods, and examples for practical use.

Qualifications

• Strong understanding of exploration geology and mineral systems, degree or equivalent experience.
• Experience developing meaningful features or structured representations from geological data for ML.
• Experience interpreting geological or spatial data using GIS, geological modeling software, Python, or R.

Responsibilities

• Find, gather, and assess project data: drillholes, assays, maps, geophysics, remote sensing, raster layers, public datasets, reports.
• Clean and standardize data while preserving geological meaning, source, resolution, and uncertainty.
• Translate geological interpretations into measurable representations for ML readiness.
• Develop prototypes or implementation specs with the ML team and document requirements, methods, and examples.

Skills

Geology knowledge

Feature engineering

GIS/spatial data

Communication & reasoning

Education

Geology or related geoscience degree

Tools

GIS

Geological modeling software

Python

R

Job description

4Point AI in Canada seeks a Geologist to advance geological data and feature development for machine‑learning models. You will gather drillholes, assays, maps, geophysics, remote sensing, and public datasets while preserving geology, source, resolution, and uncertainty.

You will translate alteration patterns and structural settings into new measurable representations, and develop prototypes with the ML team, documenting requirements, methods, and examples for practical use.