Senior AI​/ML Engineer

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.

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.

Own the models and pipelines that turn weather and satellite data into the risk and market signals Treefera's customers rely on. You will take questions such as where agricultural stress is building this season and how confident we can be about it, and build data pipelines that move from ingestion, through modelling and evaluation, to delivery to a customer.

• You take a problem end to end: an ambiguous question becomes a validated model and then a pipeline that runs repeatedly.
• You have built deep learning and statistical models for time series or spatial data, with real projects you can walk through in detail, including the parts that did not work.
• You can explain and defend every decision in the code you ship, whatever tooling helped you write it. We are enthusiastic about AI-assisted development and equally firm that you own and understand the result.
• You are fluent in the Python scientific stack (PyTorch, scikit-learn, scipy, xarray) and in the practices that make work reproducible: version control, experiment tracking, orchestration, cloud infrastructure.
• You interrogate data before you model it, you state your assumptions, and you are straightforward about uncertainty when you present a result to people who will act on it.

• Experience with weather and climate data: reanalysis products, numerical weather forecasts, weather station records, or forecast verification.
• Experience with remote sensing datasets.
• Exposure to risk modelling, financial time series, commodity markets, backtesting systematic strategies, and an interest in how a model generates a tradable signal.

• Build and ship forecasting models for environmental and risk signals, from agricultural stress indicators to weather and climate volatility, and take responsibility for how they perform once they are live.
• Extend our weather platform by adding new forecast products and capabilities to an established staged pipeline that runs ingestion, standardisation, spatial aggregation, climatology, indices and stress scoring.
• Work with satellite data across optical and radar missions to build vegetation stress signals, landcover classifications and land-surface conditions.
• Take research from prototype to production: build the infrastructure it runs on, design how it fails and how you'll know, and turn one-off work into orchestrated, reproducible data deliveries our clients rely on.
• Shape how the AI team models by improving experiment design, evaluation protocols, documentation and the treatment of uncertainty, and by communicating methods and their limits clearly to technical and commercial colleagues.

In your first 30 days you will have the weather and earth observation pipelines running locally, interrogated the system that produces our current signals, and formed your own view on where our pipelines are weakest. By 60 days you will have delivered your first improvement: a new index, a better evaluation, or a forecast product added. By 90 days that work is running in production and someone outside the AI team is relying on its output.

By six months you own a signal domain end to end, you are the person Product asks when a number looks wrong, and you can say how confident we should be in it. Within a year you will have shipped a materially better forecasting capability than the one you inherited, with the evaluation evidence to prove it.

You will report to Tommy Lees and work inside the AI pod, partnering closely with the Science team on methods, with Engineering on the platform your models run on, and with Product and Market Intelligence on what the signals need to answer for customers.

• Recruiter screen (30-45 min)
• Hiring manager interview (45-60 min)
• Team & skills session (45-60 min)
• Product interview (30 min)
• Final…