Hi there!
I’m Rodrigo Almeida, a Geo-Information, AI Researcher and Cloud Engineer focused on one of the biggest challenges and opportunities of our time: using AI to understand, predict and adapt to a changing climate.
I’m driven by the hard problems that matter to everyone. The weather and climate systems shape our economies, food security, infrastructure and daily lives and advancing AI in this space has the potential to build a safer, more resilient world.
I love working with people who care deeply about their craft and who share this mission. Satellite imagery, geospatial data and AI give us unprecedented visibility into our planet. When combined responsibly, they can improve forecasting, strengthen climate adaptation and increase global transparency. My goal is to help make this future possible.
Here is a brief overview of my professional experience, my education background and also some non-profits I've worked with over the years.
If you have any questions or remarks, feel free to reach out - I am always happy to chat!
Skills
Xarray Zarr Parquet GDAL PostGIS Computer Vision Deep Learning Machine Learning Geospatial Analysis Pulumi Prefect Slurm FastAPI Dask PyTorch Docker AWS GCP CI/CD Cloud Engineering Python
Open Source Contributions
Experience
Fraunhofer HHI | Feb 2025 ─ Present
Machine Learning Researcher, Applied AI group
- Uncertainty quantification of global AI weather models, evaluating on extreme events.
- Climate and Weather AI applications.
- View Project Details
Sabbatical | Aug 2024 ─ Jan 2025
Building up my garden in the Waldgarten Berlin and playing Touch Rugby with the Berlin Bruisers.Jua.ai | Nov 2022 ─ Jun 2024
Engineering Manager, Data team | Mar 2023 ─ Jun 2024
- Led a team of 2 engineers and worked closely with product.
- Ingested 30 different sources of historical weather observation data into a common data warehouse, using Zarr and Parquet (> 500 TB).
- Created live ETL pipelines for weather data using Prefect, deploying it in GCP and AWS.
- Lead efforts to assess data quality of weather observation data and cross-validate between sources.
- Jua raises $16M to build a foundational AI model for the natural world | TechCrunch
- A Foundational Model for Weather and Climate | ArXiv
- View Project Details
Senior Data Engineer | Nov 2022 ─ Mar 2023
- Using Zarr and Dask, created a pipeline to downscale weather forecasts to 1x1 km at the global level, 4x a day, using a deep learning model.
- Developed live ingestion pipelines for multiple weather data sources (reanalysis data and observation data), using AWS Step Functions.
Development Seed | Aug 2021 ─ Oct 2022
Cloud Software Engineer
- Developed a multi cloud (AWS and GCP) and cost efficient cloud infrastructure for running deep learning based oil slick detection with Sentinel-1 images, in the entire archive, and automatically for newly available scenes. Cerulean
- Developed an ingestion pipeline and search API that is able to handle millions of images and return similarity, at scale. Similarity Search
UP42, an Airbus company | Sep 2019 ─ Jul 2021
Senior Data Science Engineer | Jan 2021 ─ Jul 2021
- Used FastAPI to develop asynchronous micro services to estimate resource consumption of geospatial workflows.
- Developed full CI/CD pipeline for dockerized geospatial processing tools, including live and end to end tests.
Data Science Engineer | Sep 2019 ─ Dec 2021
- Developed processing chains for geospatial data in Python with Docker.
- Developed the up42-py Python package for the UP42 API and contributed to up42-blockutils.
- Built requirements for compatibility service of different geospatial processing chains.
- Conceptualised and trained deep learning model for land cover classification with satellite images using TensorFlow.
- Super-resolution of multispectral satellite images using convolutional neural networks | ArXiv
Planet | Apr 2018 ─ Aug 2019
Pre-Sales Engineer | Jul 2018 ─ Aug 2019
- Technical consultancy for prospective customers.
- Developed internal tools for reporting and data visualisation.
- Webinar - Earth Observation, Big Data and How to change the world?
- PyData Berlin - Python in the Mangroves: tracking ecosystem health from space
Internship | Apr 2018 ─ Jun 2018
- Evaluated global performance of CNN for ship detection in satellite imagery using an automated approach.
Wageningen University and Research | Sep 2017 ─ Feb 2018
Teaching Assistant
- Geoscripting
- Programming in Python
Agroop | Oct 2015 ─ Aug 2016
Account Manager and Agronomist
- Inbound and outbound sales and user support management.
- Agronomic technical assistance to customers.
- Supported the development team with user requirement reports.
MAPFRE | May 2014 ─ Apr 2015
Telemarketing Operator
GO Youth Conference | Jan 2012 ─ Mar 2012
Head of Technical Support, Design Manager
- Support with AV during the conference, graphic design, and brand development.
Education
MSc Geo-Information Science | 2016 ─ 2019
Wageningen University and Research - WUR
- Cum laude, 8.6/10 average score
- Course awarded with the Excellent Education prize (top 30 courses): Geoscripting (Period 3 2017)
- MSc thesis: Potential use of unmanned aerial vehicles for estimating fruit maturity via electronic noses: Malus domestica case study
- Assistant in conferences: KLV Alumni reunions, Competence 2016 and AGILE 2017
BSc Agriculture Engineering | 2012 ─ 2015
Instituto Superior de Agronomia - ISA, Lisbon University
- 14.1/20 average score
- Board Member of Núcleo de Agronómica (2013-2014)
- VP of the Board of Núcleo de Agronómica (2014-2015)
Publications
On the Predictive Skill of Artificial Intelligence-based Weather Models for Extreme Events using Uncertainty Quantification
DOI:10.48550/arXiv.2511.17176
Inferring Ethylene Temporal and Spatial Distribution in an Apple Orchard (Malus Domestica Borkh): A Pilot Study for Optimal Sampling with a Gas Sensor
DOI:10.1007/s13580-020-00316-9
A Comprehensive Study of the Potential Application of Flying Ethylene-Sensitive Sensors for Ripeness Detection in Apple Orchards
DOI:10.3390/s19020372
Super-resolution of multispectral satellite images using convolutional neural networks
DOI:10.48550/arXiv.2002.00580
Conferences and Workshops
NeurIPS 2025 Workshop on Tackling Climate Change with Machine Learning | 7 Dec 2025
Poster presentation
Can Artificial Intelligence Global Weather Forecasting Models Capture Extreme Events? A Case Study of the 2022 Pakistan Floods
San Diego, USA
3rd Workshop on Machine Learning for the Earth System | 25 Aug 2025
Oral presentation
Can AI weather models capture rare events? A case study of the 2022 Pakistan floods
Bonn, Germany
Volunteering
Mediator and organisation member of the Touch Rugby team – Berlin Bruisers | Oct 2023 ─ Sep 2025
Public Relations Manager, Spectrum – Student Chaplaincy and Platform | Oct 2016 ─ Aug 2018
Marketing and Communication Manager, Gymnastics Club of Almada | Sep 2012 ─ Aug 2017
President of the Board, Agronomy Students' Association of ISA | Dec 2014 ─ Sep 2015