About the company

The transition to a sustainable future requires discovering new mineral resources to power clean technologies and renewable energy solutions. From lithium for electric vehicle batteries, to copper for wind turbines, and rare earth elements for electronics — these minerals are the building blocks of our energy transition.

Lithosquare radically speeds up mineral exploration by combining foundational AI, geological expertise, and real-world data — to reduce uncertainty, prioritize the right targets, reduce costs and accelerate discovery.

Based in Paris, Lithosquare gathered an exceptional team of geologists, scientists, AI engineers, and data specialists to work as one — from field sampling to model optimization — and push the boundaries of what’s possible.

About the job

As a Geospatial Data Engineer, you will architect the data engine powering our Geology OS, building the infrastructure to process planetary-scale datasets - from satellite imagery and LiDAR to complex geological surveys. Your mission is to transform massive, unstructured multi-source data into high-performance structured databases.

You will build intelligent pipelines leveraging GenAI to handle data variability and evolve our sovereign, open-source analytics stack to monitor global operations and quantify platform value. We seek an engineer with a passion for clean data modeling and expertise in deploying open-source tools in cloud environments.

The role is based in Paris with a flexible remote working policy.

What you’ll do

• Build intelligent ingestion: design and scale robust pipelines to harvest data from diverse sources, including satellite imagery (multispectral), LiDAR point clouds, and public/private multimodal geological records;

• Implement self-adjusting pipelines: integrate GenAI/LLMs into our data workflows to create auto-adjustable pipelines capable of handling schema shifts and unstructured document extraction;

• Geospatial processing & tiling: architect high-performance systems for raster processing and vector tiling (COG, GeoJSON) to enable real-time 3D visualization and cartography;

• Own the analytics stack: architect and deploy our internal analytics infrastructure using open-source tools to monitor mining operations and field processes;

• Quantify product value: build data models and dashboards to track platform usage and quantify the scientific and economic value delivered to our geologists;

• Lead data modeling: design and maintain scalable data schemas that serve as the single source of truth for the entire company;

• Cross-functional collaboration: partner with AI engineers and geologists to align on data ingestion requirements, structural modeling, and analytics;

• Production ownership: deploy and operate data services in production (cloud services), ensuring high availability, data observability, and strict security for sensitive exploration data;

• Tech advocacy: continuously evaluate and implement emerging open-source data technologies to maintain our competitive edge in data processing.

Technical Stack

• Languages: Python (expert level), SQL (GIS), Bash

• Geospatial Libraries: GDAL/OGR, Rasterio, Shapely, Fiona, PyProj, Geopandas

• Data Formats & Tiling: GeoTIFF / COG, GeoParquet, LAS/LAZ, Zarr, Vector Tiles

• Orchestration: Temporal.io, Airflow or Dagster

• AI Integration: LLM orchestration, vector databases, prompt engineering for ETL

• Cloud & Infrastructure: Docker, kubernetes, terraform

• Analytics & BI: dbt, metabase, open-source observability tools

What we are looking for

• 5+ years of experience in Data Engineering, with a proven track record of building scalable production systems;

• Geospatial & remote sensing expertise: deep proficiency in processing raster, vector, and point cloud data, with a solid understanding of coordinate reference systems (CRS) and geospatial indexing;

• Expertise in python & SQL: ability to write highly optimized code and complex analytical queries;

• AI-Driven engineering: proven experience integrating LLMs/GenAI into data pipelines to automate the extraction and classification of complex, unstructured documents;

• Architectural vision: ability to build a modern analytics and geospatial stack from a blank slate, including tiling services (COG, MVT) for web visualization;

• Rigorous data modeling: strong foundation in data warehousing concepts and performance optimization;

• Infrastructure fluency: understanding of Kubernetes and containerized environments for deploying data workloads;

• Mission-driven: a genuine passion for the energy transition and solving "hard" physical-world problems through digital innovation

Perks & Benefits

• 🏢 Offices located in the heart of Paris

• 🌱 Strong culture of ownership & entrepreneurship, with clear growth paths as the company expand

• 🌍 Opportunity to significantly contribute to energy transition

• 👥 Collaborative work environment with world-class experts in geology, AI, and data science

• 🔄 Flexible work arrangements enabling work-life balance

• 💰 Competitive salary package

• 🍽️ Meal vouchers and premium health insurance coverage (Alan)

Join Lithosquare and become part of a passionate team driving innovation at the intersection of AI and Earth exploration. Let’s make a tangible difference together!