• Design and implement machine learning models for nature conservation using geospatial data and remote sensing technology.
• Perform experiments to validate model performance, assess accuracy, and ensure high-quality outputs.
• Apply causal inference and Bayesian methods to measure the impact of environmental interventions.
• Collaborate with scientists and engineers to align technological and scientific goals.
• Conduct code reviews and pair programming to foster collaboration.
• Mentor ML engineers and scientists on best practices in software engineering.
• Stay updated on the latest developments in machine learning and nature conservation.
• Mission-driven: Passion for nature conservation and reversing climate change.
• Machine Learning and Statistics Expertise: Proficient in Python, deep learning frameworks (e.g., PyTorch, TorchGeo), and open-source geospatial tools (Rasterio, Geopandas, Xarray).
• Causal Inference Knowledge: Experience with techniques like propensity score matching, instrumental variables, and Bayesian methods (e.g., MCMC, PyMC3).
• Experience with Geospatial Data: Familiar with working with optical and radar imagery (Landsat, Sentinel, SAR).
• Cloud Computing Expertise: Proficiency with GCP, AWS, and MLOps tools (e.g., mlflow).
• Adaptive Mindset: Comfortable with change and pivoting in a startup environment.
• Excellent Communication: Ability to collaborate across teams and document solutions clearly.
