The Role
The platform utilizes predictive modeling to reshape risk assessment in the life insurance sector—and the machine learning systems behind these models are yours to build and improve. The primary challenge isn’t just building models; it’s owning the full machine learning lifecycle—from experimentation and feature engineering to production deployment and model monitoring in a high-stakes InsurTech environment.
About the Product
The platform delivers B2B InsurTech infrastructure, utilizing machine learning, predictive analytics, and large-scale insurance data modeling to modernize life insurance underwriting, customer segmentation, churn prediction, and risk assessment. It operates at enterprise scale, handling high-volume ingestion and processing of multi-variable insurance datasets to replace legacy actuarial intuition with algorithmic precision. The system directly impacts how global insurance providers evaluate risk, forecast churn, optimize customer segmentation, and make data-driven underwriting decisions at scale.
Technology Stack: The machine learning ecosystem is built primarily on Python and SQL, leveraging Pandas and NumPy for large-scale data transformation, feature engineering, and statistical analysis across production ML workflows. Version control and collaboration ship through GitHub, maintaining a structured workflow for deployment into production machine learning pipelines. Data exploration and business storytelling are supported through advanced visualization tooling, including Seaborn, Plotly, and reporting platforms such as Power BI or Tableau.
What You’ll Be Doing
- Own the end-to-end data science lifecycle, including designing, training, implementing, evaluating, and monitoring machine learning models
- Develop and optimize predictive models across customer churn, forecasting, segmentation, classification, and regression use cases
- Collaborate closely with product managers and customers to understand business needs and build data-driven solutions together
- Identify and apply the right combination of analytics, experimentation, causal inference, and machine learning techniques to solve complex business problems
- Present research findings, model performance, and analytical insights to stakeholders across all levels of the company
What We Expect
Must-have
- 3+ years of professional experience in Machine Learning or Data Science
- BSc in Computer Science, Mathematics, Statistics, Physics, or a related quantitative field (MSc / PhD is an advantage)
- Strong proficiency in Python and SQL
- Hands-on industry experience taking ML models from experimentation to production, including work with time series, clustering, regression, and classification algorithms
- Strong skills in data exploration, analysis, and visualization
- Strong problem-solving skills with the ability to break down complex challenges into smaller, actionable components
- Collaborative mindset, positive attitude, and strong communication skills
- Upper-Intermediate (B2) English level or higher
Nice-to-have
- Experience in the Insurance, InsurTech, or FinTech domains
- Experience working with reporting and visualization tools such as Power BI or Tableau
Why This Role Is Worth Your Time
- You are building predictive models that directly modernize a traditionally conservative, multi-billion-dollar global industry—your analytical outputs shift insurance from intuition to precision
- Direct collaboration with an R&D organization combining machine learning, actuarial science, and product strategy—giving you exposure to real production ML systems in a high-impact domain
- Real production-scale ML complexity: you will work with high-volume, multi-variable enterprise datasets where model quality, feature precision, and production reliability have direct business impact
