SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Treefera is seeking a Senior AI/ML Engineer to own the models and data pipelines that transform weather and satellite data into risk and market signals for agricultural and climate applications.
In this role, you will take problems end-to-end: from ambiguous business questions through validated models to production pipelines that run repeatedly. You'll build and ship forecasting models for environmental and risk signals—including agricultural stress indicators, weather and climate volatility, and land-surface conditions. You'll work with satellite data across optical and radar missions to develop vegetation stress signals and landcover classifications. Your responsibilities include extending Treefera's weather platform with new forecast products, taking research from prototype to production, and shaping how the AI team approaches modeling through improved experiment design and uncertainty communication.
Key deliverables span a clear progression: within 30 days, you'll have the weather and earth observation pipelines running locally and have interrogated the current signal-generation system. By 60 days, you'll have delivered your first improvement (a new index, better evaluation, or forecast product). By 90 days, that work runs in production with external stakeholders relying on it. Within six months, you'll own a signal domain end-to-end and be the person Product consults when numbers need validation. Within a year, you'll have shipped a materially better forecasting capability than your predecessor, with evaluation evidence to prove it.
You will interrogate data before modeling, state your assumptions clearly, and be straightforward about uncertainty when presenting results to decision-makers. You'll work with the Python scientific stack and reproducible practices including version control, experiment tracking, orchestration, and cloud infrastructure.
REQUIREMENTS:
- Deep expertise building deep learning and statistical models for time series or spatial data, with real projects you can walk through in detail (including failures)
- Fluency in Python scientific stack: PyTorch, scikit-learn, scipy, xarray
- Strong practices in reproducibility: version control, experiment tracking, orchestration, cloud infrastructure
- Ability to explain and defend every decision in shipped code
- Comfort with AI-assisted development while maintaining full ownership and understanding of results
Desirable experience:
- Weather and climate data (reanalysis products, numerical weather forecasts, weather station records, forecast verification)
- Remote sensing datasets
- Risk modeling, financial time series, commodity markets, backtesting systematic strategies, and understanding how models generate tradable signals
