Machine Learning Engineer - £110k – £130k – Geospatial Tech 4 GoodMachine Learning | Deep Learning | Time Series | Climate | Remote Sensing | PyTorch | scikit-learn | Geospatial | AWS | MLOps | Python | Risk Modelling | FinTech |Do you want to work with a business building AI-native data system that bring clarity and credibility to nature-based assets?A business tackling complex, real-world environmental challenges, helping organisations make high-impact decisions around risk, resilience and commercial performance?This is the chance to join as a Machine Learning Engineer working with a climate-tech scale-up applying cutting-edge Machine Learning to satellite data, weather models and environmental signals, reshaping how nature is valued in real-world decision-making.Joining their AI team, you’ll design and deploy models that forecast climate volatility, detect vegetation stress, and generate risk-driven insights from remote sensing and time-series data. You’ll work across AI, climate science, geospatial modelling and scalable pipelines, contributing meaningfully from day one.What you’ll be working on:
• Building and evaluating Machine Learning/DL models for satellite, weather and climate data
• Forecasting environmental and risk-related signals (volatility, vegetation stress, land-surface change)
• Developing geospatial and remote-sensing models (Sentinel-1/2, GEDI, optical, radar, LiDAR)
• Creating time-series and forecasting models for environmental change
• Translating business questions into robust modelling problems
• Turning research prototypes into scalable, reproducible AI pipelines
• Communicating assumptions, uncertainty and results clearlyThe must-haves:
• Strong background in Machine Learning, DL and Applied Statistics
• Time-series modelling + backtesting
• Experience with geospatial and climate datasets
• Python stack: PyTorch, scikit-learn, scipy
• Reproducible workflows (Git, AWS/cloud, W&B)Nice-to-haves:
• Risk modelling, financial time series, portfolio optimisation (great for FinTech/quant backgrounds)
• Climate/weather datasets (CMIP, forecast data)
• Geospatial tools: rasterio, xarray, geopandas, GDAL
• Remote sensing (optical, radar, LiDAR)
• MLOps: CI/CD, containerisation, monitoring
• Startup or fast-paced product environmentThe role offers £110k–£130k, a global team environment, and the chance to shape the future of AI-powered environmental and risk intelligence.If it ticks those boxes, don’t hang about message me: Machine Learning | Deep Learning | Time Series | Climate | Remote Sensing | PyTorch | scikit-learn | Geospatial | AWS | MLOps | Python | Risk Modelling | FinTech |