Main
Willian Vieira PhD
Data scientist with a PhD in quantitative ecology who learned to extract signal from messy, uncertain spatial data. I combine Bayesian and machine learning statistics with data engineering practices to build automated, scalable pipelines. My focus is on making complex datasets reliable, accessible, and directly useful in decision-making.
Experience
Data Analyst
Habitat, Montreal, Canada
N/A
2025 - 2024
(1 yr 9 m)
Delivered custom geospatial machine learning models for client decision-making | Built and maintained reproducible pipelines in R, Python, and Julia for cloud-hosted spatial data | Designed a lakehouse architecture for streaming vector and raster datasets via cloud storage | Developed a metadata-driven pipeline framework enabling scalable Azure processing and improved data governance | Modernized workflows with containerization, CI/CD, and DevOps practices | Led the team-wide transition from Windows to Linux, validating full workflow compatibility and building an automated provisioning script to setup new Linux machines
Biostatistician
Environment and Climate Change Canada - Quebec, Canada
N/A
2022 - 2020
(part-time)
Developed a standardized sampling protocol ensuring unbiased, representative boreal bird surveys in Quebec | Led R&D to correct spatial bias from legacy survey sites, creating a novel method later adopted across other Canadian provinces | Produced a fully reproducible, open workflow with automated reports documenting methods and results
Code: , Report:
Teaching Assistant
Université de Sherbrooke - Sherbrooke, Canada
N/A
2022 - 2018
(part-time)
TA for undergraduate biology (+4 cohorts of ~40 students): Introduction to Scientific Programming and Methods in Computational Ecology | Contributed to course materials and built CI/CD pipelines to render and deploy teaching content | TA (1 yr) for undergraduate Probability & Statistics in engineering | TA for graduate Biodiversity Modelling Summer School, teaching Bayesian modelling with Stan
Education
PhD, Ecology
Integrative Ecology Lab - Université de Sherbrooke, Canada
N/A
2024 - 2017
How climate, competition, and forest management shape the limits of tree species distributions: from individuals to metapopulations
Mathematical modeling | Hierachical models | Bayesian statistics | Machine Learning | High Performance Computing (HPC) | Open Science
Masters 2, Agroecology and Resource Management
Bordeaux Sciences Agro, Bordeaux, France
N/A
2016 - 2015
Modelling the dispersion of weed species in agricultural landscapes
BSc in Agronomy
Universidade Federal de Santa Catarina, Florianópolis, Brazil
N/A
2015 - 2010
Defaunation impact on a threatened species: araucaria in southern Brazil