Data Scientist

#LIHybrid Norstella is a collection of leading pharmaceutical solutions providers – Evaluate, MMIT, Panalgo, The Dedham Group, Citeline – that assist clients in navigating complexities at every stage of the drug development cycle, from pipeline to patient. For further information, please visit Norstella.com. Evaluate is an international company offering excellent market intelligence services for the Pharmaceutical, Medical Device, Financial and Consulting sectors, through the Evaluate Pharma®, Evaluate Medtech®, Evaluate Omnium, and Evaluate Vantage® online brands. Our worldwide clients in Pharma and Biotech, Medtech, Banking, and Consulting view Evaluate Pharma® as the industry standard for timely and accurate analysis of reported drug sales, consensus sales forecasts, R&D pipeline, markets, and comprehensive company financials. THE TEAM In this role as a Data Scientist, you will report to the Lead Data Scientist for Strategic Intelligence and Market Access, within the Data Science Department. You will design and implement advanced models to assist in the development of new products. We have small, multi-functional teams of pharmaceutical industry experts, R&D, data engineers, and data scientists to quickly prototype new visualizations and interactive reports using both our current and newly obtained datasets. SCOPE OF THE ROLE In this role as a Data Scientist, you will: - Apply your basic knowledge of machine learning, generative AI, and other DS techniques to identify opportunities and help shape product development. - Use Python and AWS SageMaker to create knowledge generation algorithms applied to pharmaceutical products. - Visualize and analyze the performance of your models with common Python libraries. - Work with data engineers and DevOps to deploy your models into production environments. - Contribute to our growing in-house data science library of useful functions, data handlers, APIs and other modules. HOW YOU’LL SUCCEED Our ultimate objective is to facilitate patient access to life-saving treatments. You will collaborate with R&D pharma specialists to understand a problem that impedes the development and release of effective new pharma products that we think we can assist with. After understanding the problem, you will conceptualize potential solutions. Previously our solutions have included classical machine learning, fine-tuning massive language models, or just well-thought-out data transformations and business logic. We are more focused on elegant solutions to problems rather than the technology utilised. After considering potential solutions, you will team up with data engineering to gather data from a wide range of sources and build a proof-of-concept your algorithm. You will deliver indicative results from your PoC into datasets for visualisation and exploration by the broader multi-functional team. You will also perform code reviews with the data science team to explain your approach, its strengths, and weaknesses. After refining the design with the multi-functional team as part of customer-led product development, you might convert your prototype into a full-fledged product. This will include containerising your code to a high standard and deploying your algorithm, usually as an API in AWS SageMaker. Over time you may revisit this product, assess its performance, and retrain/improve as needed. Requirements - A master's degree or higher in a STEM field such as Maths, Physics, Computer Science, Engineering, or equivalent practical experience. - Excellent knowledge of Python and core data science libraries, including pandas, numpy, sklearn, scipy, CatBoost, XGBoost, HuggingFace, and similar libraries. - Ability to design and iterate creative solutions in Jupyter notebooks. - Ability to turn successful code into well-engineered packages with the appropriate use of built-in classes, modules, high/mid/low-level functions, and other Python best practices. - Excellent statistical knowledge, particularly in relation to training dataset weaknesses and DS model scoring. - Experience with building products that leverage large language models and generative AI. - Ability to work with stakeholders to manage your projects independently. - Ability to explain your technical decisions on a project to non-data scientists. Nice to have - Experience with AWS, particularly regarding ML workflows with SageMaker, serverless compute and storage such as S3 and Snowflake. - Knowledge of the pharmaceutical industry, specifically the stages of pharmaceutical product development. - Data visualisation skills with Matplotlib, Bokeh, Seaborn, Plotly or similar libraries. Benefits - 25 days holiday (increasing to 30 over 9 years) + 8 bank holidays. - Value You Day - an additional wellbeing day on top of your holiday allowance. - Pension plan - company contribution of 6.7% increasing to 10% after 12 months of service. - Life Assurance 4 x salary. - Employee Assistance Program (EAP). - Private Medical Insurance - Corporate Gym Membership/Discount - Flexible working and flexitime policies. - Season Ticket Loan. - Cycle to Work Scheme. - Maternity, Paternity, & Adoption leave – including enhanced leave for 2+ years’ service. - Shared parental leave. Evaluate is an equal opportunities employer and does not discriminate on the grounds of gender, sexual orientation, marital or civil partner status, pregnancy or maternity, gender reassignment, race, color, nationality, ethnic or national origin, religion or belief, disability, or age. We respect and value people’s differences, to help everyone achieve more at work as well as in their personal lives so that they feel proud of the part they play in our success. All decisions about people at work should be based on the individual’s abilities, skills, performance, and behavior, and our business requirements. Evaluate operates a zero-tolerance policy to any form of discrimination, abuse or harassment.