Data Scientist (Insurance)

Location: London, United Kingdom; hybrid working

Company

hirify.global operates in the insurance sector, working with commercial underwriting and actuarial teams.

What you will do

• Deliver data science projects from data preparation and exploratory analysis through model development, validation, production delivery, deployment, and monitoring.
• Apply data science to automate manual processes and produce ad hoc analytics and business insights.
• Explore generative AI use cases and assess their value and suitability for the roadmap.
• Assess internal and external data sources with data scientists and actuaries, and work with IT and Data Engineering on project data.
• Write tested, version-controlled Python, contribute to code reviews and Azure ML pipelines, and monitor adoption and performance of deployed products.
• Engage with underwriting teams, capture requirements, and communicate findings, limitations, and uncertainty to technical and non-technical audiences.

Requirements

• Solid Python for data science, including readable, structured code and understanding of functions, classes, and modules.
• Machine learning knowledge across standard tools such as scikit-learn, pandas, NumPy, and statsmodels or equivalents, with sound validation judgment.
• Statistical foundations including hypothesis testing, regression, uncertainty quantification, and recognising unsupported conclusions.
• SQL skills for efficiently querying and joining relational data.
• Experience with data wrangling and preprocessing of ambiguous, incomplete, and inconsistent data.
• Working knowledge of Git and version control.
• Clear written and verbal communication, including explaining technical work to non-technical colleagues.
• Curiosity about the business, a growth mindset, pragmatism, reliability, collaboration, and willingness to take ownership of development and delivery.

Nice to have

• Evidence of linking analytical work to business outcomes, and experience working with stakeholders on requirements or adoption.
• Insurance experience, particularly in the Lloyd's market, pricing, underwriting, or actuarial methods.
• Object-oriented design, automated testing such as pytest, and regular code review practice.
• Experience taking models into production or contributing to production models.
• Exposure to MLOps and CI/CD, including pipeline orchestration, model versioning, automated deployment, and monitoring.
• Dependency and environment management, including virtual environments or Docker.
• Distributed processing frameworks such as PySpark, and data visualisation or reporting tools such as Power BI.

Culture & Benefits

• Hybrid working and support for flexible working practices.
• Pairing, code review, and hands-on project work to develop software engineering, cloud ML, and MLOps skills.
• Values include fairness and respect, openness and inclusion, ambition, continuous improvement, and investment in employee potential.
• Equal-opportunities employer committed to a diverse and collaborative working environment.
• Reasonable adjustments are available during the application process on request.