Expert Data Science, PCS

Major accountabilities:

• Apply standard data science, statistical and machine learning methods to support research, operational and business questions across relevant scientific and functional areas.
• Perform data extraction, cleaning, transformation, integration and quality checks from multiple structured and unstructured data sources to enable reliable analysis.
• Conduct text data mining as a core responsibility, including processing, structuring and analyzing text-based data sources to identify trends, entities, relationships, classifications and insights relevant to project objectives.
• Support natural language processing activities, including text preprocessing, feature extraction, classification, clustering, entity recognition, topic modelling and evaluation of text-based analytical outputs.
• Build, validate and document predictive models, exploratory analyses, dashboards and visualizations under the supervision of more experienced data scientists.
• Contribute to the development of reproducible analytical pipelines using appropriate programming languages, libraries and version-control practices.
• Present analytical findings in a clear, concise and visually effective manner to project teams and business stakeholders, highlighting assumptions, limitations and recommended next steps.
• Collaborate with scientists, pathologists, data engineers, software engineers and other stakeholders to understand requirements, define analytical approaches and deliver timely outputs.
• Support evaluation and adoption of relevant data science tools, packages, visualization approaches and automation opportunities to improve efficiency and quality.
• Maintain awareness of current developments in data science, machine learning, natural language processing and analytics methods, and apply learnings to assigned tasks where appropriate.
• Ensure that work is performed in accordance with applicable data governance, privacy, documentation, quality and compliance requirements

Minimum Requirement:

• Bachelor’s/ master’s degree in data science, Computer Science, Statistics, Mathematics, Bioinformatics, or a related quantitative discipline.
• Approximately 2 -4 years of relevant professional experience in data science, applied analytics, machine learning, bioinformatics, computational biology or a related field.
• Must have practical experience with text data mining, natural language processing or analysis of unstructured text data.
• Proficiency in Python and common data science libraries such as pandas, NumPy, scikit-learn, matplotlib, seaborn or equivalent tools.
• Experience with statistical analysis, exploratory data analysis, predictive modelling and model evaluation. Experience preparing, cleaning and integrating data from multiple sources.
• Familiarity with databases and query languages such as SQL.
• Ability to create clear data visualizations and communicate analytical results to technical and non-technical audiences.
• Basic understanding of machine learning concepts including supervised learning, unsupervised learning, feature engineering, model validation and performance metrics. Familiarity with version control, preferably Git, and reproducible coding practices.