Data Scientist

Who We Are

FIS is Italy’s leading company in the development and production of active pharmaceutical ingredients and intermediates for the global pharmaceutical industry.

With three manufacturing sites and more than 2,300 professionals, we have been committed for nearly 70 years to research, quality, and sustainability.

Our products help improve the lives of millions of people worldwide—a responsibility we embrace with pride and passion.

Join our team and become part of a company that grows through the dedication of the people who shape it every day.

The role

We are looking for a Data Scientist to join our team and contribute to the development and industrialisation of analytical and artificial intelligence models in support of our Operations, R&D and Finance functions.

The ideal candidate combines strong statistical and machine learning skills with a clear focus on production deployment and business impact. They will operate in a cross-functional environment, working closely with data engineers, architects and business stakeholders to turn data into actionable insights and concrete predictive solutions.

Key responsibilities

AI model development and validation

• Design, develop and validate predictive and prescriptive AI models
• Conduct exploratory analysis, feature engineering and variable selection to improve model performance
• Ensure model robustness and interpretability through rigorous validation techniques (cross-validation, backtesting, explainability)
• Document methodologies, assumptions and results clearly and in line with internal standards

Industrialisation and MLOps

• Translate analytical prototypes into scalable, production-ready solutions, applying robust and maintainable coding standards
• Develop automated training, scoring and AI model deployment pipelines in collaboration with the Data Engineering team
• Implement continuous model performance monitoring systems (data drift, accuracy decay, alerting) to ensure long-term reliability in production
• Contribute to defining and adopting MLOps best practices within the team

Generative AI

• Develop and experiment with solutions based on Large Language Models (LLMs) and generative AI architectures for business use cases (e.g. document synthesis, decision support, cognitive process automation)
• Evaluate and implement Retrieval-Augmented Generation (RAG) techniques and prompt engineering for enterprise applications
• Collaborate with business teams to identify generative AI application opportunities and prototype high-value solutions

Collaboration and business impact

• Engage with business stakeholders to understand analytical needs, define requirements and communicate findings in an effective and accessible way
• Translate complex analytical insights into actionable recommendations that support business decision-making
• Contribute to building a data-driven culture within the organisation through knowledge sharing and internal training

Requirements

Education and technical skills

• Degree in Data Science, Statistics, Mathematics, Engineering, Computer Science or related disciplines
• At least 3–5 years of proven experience in developing and deploying machine learning models in structured organisational contexts
• Strong command of Python and key data science and ML libraries (pandas, scikit-learn, TensorFlow, PyTorch or equivalent)
• Experience with cloud platforms for model training and deployment (e.g. Azure ML, AWS SageMaker or equivalent)
• Knowledge of MLOps tools for managing the model lifecycle (e.g. MLflow, Airflow, Kubeflow or equivalent)
• Familiarity with NLP, LLM and generative AI techniques (RAG, fine-tuning, prompt engineering)

Nice to have

• Experience in regulated industries (pharmaceutical, life sciences, chemical) with strict traceability and validation requirements
• Knowledge of industrial processes (manufacturing, supply chain, R&D) and ability to contextualise models within the application domain
• Experience with explainability techniques and responsible AI in enterprise contexts
• Familiarity with big data and distributed computing environments (Spark, Databricks or equivalent)

Soft skills

• Structured analytical thinking and ability to tackle complex problems with a pragmatic approach
• Excellent communication skills with both technical and non-technical stakeholders, with the ability to translate complex analyses into clear messages
• Team player attitude in agile, cross-functional teams, with a strong focus on delivery and business value
• Intellectual curiosity and a continuous learning mindset towards emerging methodologies and technologies

What we offer

• The opportunity to contribute to a high-impact AI transformation project
• Exposure to real and challenging use cases, with full ownership of the model lifecycle — from prototyping to production
• A collaborative work environment with highly qualified, innovation-driven teams