OXMAN - Machine Learning Research Engineer

• Develop machine learning models for geospatial inference of key ecosystem metrics, leveraging geospatial AI to synthesize environmental data into actionable parameters for ecosystem design and simulation. • Develop and refine advanced deep generative models and reinforcement learning algorithms for built-environment design. • Contribute to decision-making frameworks that combine procedural generation with ML and data-driven optimization. • Collaborate with computational ecologists and data scientists to integrate generative design with ecosystem simulation models. • Align design outputs with ecological performance indicators such as species richness and carbon sequestration. • Prepare detailed technical documentation and contribute to model validation using empirical ecological data. • Key Goals and Outcomes • Research and development of high-fidelity Geospatial AI models for the automated inference of ecosystem metrics across varied scales. • Utilize inferred geospatial data to drive the computational synthesis and design of functional, resilient ecosystems. • Establish a robust pipeline for integrating remote sensing and geospatial data into generative design workflows. • Deliver scalable ML frameworks that provide real-time or near-real-time feedback on ecological performance (e.g., carbon sequestration and biodiversity). • Develop innovative design methods that support and enhance ecological processes through data-driven optimization.