Junior Data Scientist

Company Details Berkley Oil & Gas, a W. R. Berkley Company, is an insurance underwriting manager offering specialized property and casualty products and risk services to customers in the energy sector. Our customers value the expertise we bring and appreciate working with professionals who understand their business. We are committed to delivering innovative products and exceptional service to our employees, agents, and brokers. Berkley Oil & Gas remains dedicated to staying informed about the evolving dynamics of the industry, supporting efforts to minimize and mitigate risks in the oil patch, and continually improving our products and services to meet customer needs. W. R. Berkley Corporation, founded in 1967, is one of the nation’s premier commercial lines of property and casualty insurance providers. Each of the operating units in the Berkley group participates in a niche market requiring specialized knowledge about a territory or product. Our competitive advantage lies in our long‑term strategy of decentralized operations, allowing each of our units to identify and respond quickly and effectively. Company URL: The company is an equal opportunity employer. Responsibilities The Data Scientist designs, builds, and delivers analytical solutions that support underwriting, pricing, and operational decision‑making. The role performs exploratory data analysis, feature engineering, data pipeline development, and predictive modeling, working closely with business and technical partners to ensure solutions are accurate, scalable, and aligned with business goals. Business Understanding & Solution Design Partner with business stakeholders to define analytical needs and prototype solutions Evaluate the business value of internal and third‑party data sources using standardized assessment criteria Build foundational understanding of relevant insurance and energy domain concepts Data Discovery, Exploration & Engineering Conduct exploratory data analysis to assess data quality, structure, coverage, and predictive potential Build and refine data pipelines using SQL and Python Develop entity‑matching methods, including geospatial and temporal techniques Engineer and maintain features that support analytical and predictive modeling Model Development & Experimentation Build and evaluate predictive models, comparing performance against benchmarks Quantify expected business value, costs, and ROI for proposed solutions Design repeatable workflows for modeling, experimentation, and evaluation Deployment, Integration & Monitoring Collaborate with engineering teams to integrate analytical models into production systems Implement monitoring to ensure data and model quality over time Identify opportunities for iteration and performance improvement based on results and business feedback Collaboration, Communication & Project Delivery Work with cross‑functional teams to clarify requirements and acceptance criteria Prepare analytical datasets, dashboards, and reports that support decision‑making Communicate insights clearly to technical and non‑technical stakeholders Quality, Documentation & Automation Conduct quality assurance checks on datasets, metrics, and models Maintain documentation for data sources, features, models, and workflows Automate repetitive or manual tasks using scripting and AI tooling Qualifications Experience & Professional Skills 2–5 years of experience in data science or a related analytical field, including exposure to model deployment and monitoring Strong sense of ownership, urgency, and self‑motivation Excellent written and verbal communication skills; able to convey complex concepts clearly Effective collaborator with experience in cross‑functional, team‑oriented environments Prior quantitative research experience through academic work, personal projects, or previous roles Technical Skills Proficiency in Python (pandas, NumPy, scikit‑learn) and SQL; solid understanding of databases and data modeling Experience conducting exploratory data analysis, including profiling, handling missing data, and outlier detection Feature engineering experience, including geospatial, temporal, and derived features Familiarity with version control (e.g., GitHub) and cloud analytics platforms (e.g., Databricks) Understanding of Agile or SDLC practices Domain Knowledge Familiarity with Oil & Gas or Property & Casualty insurance concepts is a plus Education Requirement Master’s degree in data science, analytics, statistics, computer science, engineering, or related field. Additional Company Details We do not accept any unsolicited resumes from external recruiting agencies or firms. The company offers a competitive compensation plan and robust benefits package for full time regular employees. The actual salary for this position will be determined by a number of factors, including the scope, complexity and location of the role; the skills, education, training, credentials and experience of the candidate; and other conditions of employment. Sponsorship Details Sponsorship not Offered for this Role #J-18808-Ljbffr