Machine Learning Specialist
Pubblicato il 17-10-2026 - Agenzia del Lavoro Trentino in Rovereto
AMIGO Srl is the first Italian SME working on climate services. Founded in 2013 by two climate scientists with a wide experience in management and entrepreneurship, AMIGO has a passionate team of experts specialised in the development of innovative IT-based climate services in different sectors, i.e. energy, food and agriculture, water management, re/insurance, and infrastructure. AMIGO’s solutions synergise the best available climate data from satellite observations, modelling products, and in-situ measurements through state-of-art techniques of machine learning, statistical analysis, and numerical modelling. Co-design is the pillar of AMIGO’s innovation, to ensure that the solutions are tailored to the end user’s needs and are an added-value in the decision-making process.
The company works on a number of topics including:
- Development and improvement of skilful climate forecasts
- Co-design of tools for managing climate risk for a range of sectors, e.g. renewable energy generation
- Early-warning systems to foster the resilience of the energy sector to climate extremes.
AMIGO collaborates with research institutions and universities in Europe, Africa, North America, South America, and Australia, and with international organisations such as the World Meteorological Organisation.
AMIGO has also been the contractor or key partner of a variety of projects funded by the EU,
intergovernmental organisations, and regional administrations.
As AI/Machine-Learning Specialist, you will build AI/Machine-Learning models, design and implement algorithms with the aim of gaining insights and extracting information from complex, geo-spatial data. You will join a highly innovative SME, collaborating with a multi-disciplinary team on a wide range of problems in different climate-sensitive sectors.
Your role
- Designing, developing and deploying new and improved AI/Machine Learning algorithms
- Conducting data analysis, feature engineering, and model evaluation to improve accur