🌱 Our Mission

At Treeconomy, we believe in the regenerative power of nature. We’re on a mission to combat climate change, restore ecosystems, and improve livelihoods. By embracing remote sensing technology and financial innovation, we are revolutionising the forest carbon market and incentivising landowners to grow flourishing, climate-positive forests. We have massive goals and are looking for passionate people to help us achieve them.

🚀 Our Company

Treeconomy is a venture-backed earth-tech startup working at the intersection of technology, ecology, and finance. We were founded to close the $700B annual nature funding gap, scaling impactful nature-based solutions to realise true win-win-wins for climate, biodiversity, and human livelihoods. We harness a fusion of satellite imagery, drone data, and machine learning to bring traceability, transparency, and trust to impactful carbon-removing restoration efforts. We specialise in developing advanced digital Monitoring, Reporting, and Verification (dMRV) systems to accurately measure carbon sequestered by nature-based projects. Our work supports landowners and investors, connecting the highest-quality projects to leading corporate carbon buyers and investors via our platform.

✨ The Role

We’re hiring a Machine Learning Scientist/statistician on a contract basis to lead the research and development for a groundbreaking R&D project, "QUBIST: Quantifying Uncertainty in Biomass using Integrated Satellite Technologies".

This project directly addresses a critical barrier in the Voluntary Carbon Market: the lack of transparent, robustly quantified uncertainty in carbon stock estimates. Your mission will be to develop a cutting-edge methodology that improves, develops and integrates our current Bayesian statistical models with multi-mission satellite data to produce more accurate and trustworthy carbon stock data.

This is a high-impact role focused on pioneering a more honest and statistically sound approach to carbon measurement. You will be responsible for the core technical research and model development, turning a scientifically ambitious concept into a pilot-tested prototype. Success in this project will not only enhance our commercial dMRV offering but also contribute valuable knowledge to the wider UK climate sector, building the trust needed to unlock significant private finance for nature.

You will report to our Science Lead, Dr. Matt Amos, and work closely with our remote sensing and product teams.

Primary objectives for the contract

• Methodology Specification: Conduct a detailed literature review and finalise the specific Bayesian methodology for the project.
• Prototype Development: Develop a functioning alpha version of the Bayesian model capable of integrating multiple satellite data sources.
• Validation & Testing: Validate the prototype model against ground-truth field data from at least two pilot sites, producing a comprehensive performance report.
• Dissemination: Contribute to a final project report and a public-facing whitepaper to share the project's findings with the wider sector.

🌳 Your Profile

We are looking for a specialist with skills in Bayesian statistics and applied machine learning, who is excited to tackle a fundamental scientific challenge with real-world impact.

Must-haves

• Deep expertise in advanced statistics, particularly Bayesian inference and hierarchical modelling.
• Hands-on experience with probabilistic programming languages (e.g., PyMC, tensorflow, numpyro).
• Strong proficiency in Python and its data science ecosystem for handling large, complex datasets.
• A proven track record of leading independent research projects, from conceptualisation and literature review through to model development and validation.
• Excellent ability to communicate complex statistical concepts clearly to both technical and non-technical audiences.
• Comfort operating in a startup environment: ambiguity, fast iteration, and principled trade-offs.

Nice-to-haves

• PhD or MSc in a quantitative field such as Statistics, Machine Learning or Environmental Data Science.
• Experience processing and fusing multi-mission satellite data, especially spaceborne LiDAR (e.g., GEDI, ICESat-2).
• Familiarity with advanced Bayesian computational methods such as variational inference.
• Experience using cloud infrastructure (e.g., AWS, GCP) for large-scale data processing and running complex model simulations.
• Exposure to the climate-tech sector, particularly dMRV, forestry, or the Voluntary Carbon Market.
• Experience working with geospatial data and relevant open-source tools (e.g., QGIS).

🧰 Tech Stack & Collaboration

• Core Research: Python, JAX/torch, Geospatial libraries (xarray, Rasterio, GeoPandas, GDAL).
• Infrastructure: Cloud computing platforms for model training and data processing (primarily GCP).
• Collab & delivery: Slack, Notion (docs), GitHub (PRs).

🌍 Location & hours

• UK-based, with core hours 10:00–16:00 for collaboration.
• Remote-friendly (within the UK). Ability to travel to London desirable once a month.

📄 Contract

• Position: Machine Learning Scientist
• Time commitment: Full-time (5 days/week), initial 6-month term. We anticipate extending this into a permanent contract upon successful completion of the project.
• Start date: ASAP.
• Pay guidance: £55-75k annual.
• Equipment: A company laptop can be provided if needed.

🤝 How we work together

We value researchers who bring clarity and scientific honesty. You’re comfortable stating what’s true—especially when it’s inconvenient—and explaining what’s happening, why it matters to users and the business, and what you recommend next. You favour robust, well-validated solutions and steady delivery over clever complexity.

🎉 Ready to Apply?

Excited by the chance to build a system that fundamentally improves trust in nature-based climate solutions? We’d love to hear from you—even if your profile isn’t a perfect match. We will be reviewing applications on a rolling basis until the position is filled.

Apply via the form on the page