Job Opportunities API

GROW WITH TREEFERA We are a first-mile intelligence platform, delivering granular visibility into the point of origin in global ag & soft commodity supply chains - where risk, cost, performance and exposure are set. [https://app.ashbyhq.com/api/images/user-content/c732ad7a-0ae4-498f-b42a-bf284905cf4d/eaa3e7e4-29ff-4c00-86a8-f04fab8ec14a/Screenshot%202026-04-29%20at%2015.07.01.png] You’ll join a global, cross-functional team that values rigour, curiosity and working close to real-world challenges. Whether your focus is AI, climate, product or operations, you’ll have space to contribute meaningfully and make an impact from day one. If you’re excited by complex problems and want to help reshape how nature is valued in real-world decision-making, we’d love to hear from you. ROLE OVERVIEW Transform satellite, radar, and LiDAR signals into precise intelligence that protects forests and fortifies supply chains. You will develop models ranging from EUDR-compliant plantation mapping, to biomass estimation and forest degradation that accelerate decarbonisation and in turn enable confident, risk-adjusted decisions at global scale. WHO YOU ARE - You take models across the full lifecycle — research, prototyping, validation and productionisation — and you have shipped them in an industry, product or startup setting, not only in research. - You are fluent across the modern Python ML stack — deep learning (CNNs, U-Nets, vision transformers) in PyTorch and classical methods (gradient boosting, random forests) in scikit-learn — and you pick the right approach for the problem. - You work fluently with remote sensing data (optical and SAR) and geospatial Python tooling (rasterio, xarray, geopandas, GDAL and the STAC ecosystem), and you understand the sensor-specific quirks that matter for modelling. - You design validation that benchmarks against reference datasets, quantifies uncertainty and surfaces failure modes — and you can explain modelling choices, uncertainties and trade-offs to scientific and non-scientific stakeholders alike. - You collaborate by default across Science, Engineering and Product, bring domain exposure to deforestation, land-use change, biomass or supply-chain transparency, and have a genuine appetite for AI-assisted development workflows. Desirable requirements (if applicable): - Building on EO foundation models as a downstream substrate — lightweight classifiers, regressors or similarity search on frozen embeddings (e.g. AlphaEarth Foundations, Clay), with fine-tuning or pretraining where the case justifies it. - Multi-modal fusion across optical (Sentinel-2, Landsat), SAR (Sentinel-1, PALSAR) and LiDAR (GEDI, ICESat-2), and time-series modelling for environmental change detection (temporal transformers, sequence or self-supervised approaches). - Familiarity with STAC-based catalogues (Google Earth Engine, Microsoft Planetary Computer, AWS Open Data), AI-assisted development as a core part of your workflow, and working cross-functionally alongside solutions architects, sales and engineering. WHAT THE JOB INVOLVES - Design, train and evaluate models — from gradient boosting to CNNs, U-Nets and vision transformers — for commodity and plantation mapping, land-cover classification, change and disturbance detection, and biomass / canopy-height estimation. - Build embedding-driven workflows on top of EO foundation models — few-shot classifiers, similarity search and downstream regressors. - Design validation strategies that benchmark outputs against plot inventories and third-party reference data, quantify uncertainty and surface failure modes — producing QA artefacts (maps, plots, model cards, error analyses) that internal teams and clients can defend. - Partner with Engineering to take models into scalable, reproducible inference pipelines across millions of plots. - Contribute to a strong research culture across Science, AI and Engineering — revie