Medical Data Scientist
Does supporting world-class research and improving lives of patients excite you? Our dynamic and internationally recognised research company Observation & Pragmatic Research Institute, (OPRI) is looking for a highly motivated and dynamic member to join our data team. The role can be based in one of our Singapore, Cambridge, or Brisbane offices. For experienced individuals, remote working may also be considered. In this role you will be working alongside our research, statistical and database teams.
This is a fantastic opportunity to gain experience within an internationally recognised research organisation involved in the analysis and dissemination of data from large-scale observational studies and pragmatic randomised controlled trials.
The successful candidate will have experience of working in health research data, have a high attention to detail, a proactive approach and strong time management skills.
- Provide support on database querying, population, and reporting, using structured query language (SQL)
- Statistical analysis using R
- Generate data releases following study protocol requirements and service reports (Jupyter notebooks, RMarkdown)
- Improve the interpretation of medical free text with Natural Language Processing skills
- Advise internal team members and external clients on study database(s) content
- Engage in building and maintaining data dictionaries and system technical documentation
- Undertake quality checks to assure high standards of data and code
- Contribute to data analyses as required for research projects
- Maintain compliance with information governance and company policies
MSc preferred, with strong technical or scientific component (e.g. Computer Science, Math, Statistics). BSc or equivalent will be considered for candidates with additional relevant experience.
- A minimum of five years’ relevant experience (minimum of three years if applicant holds a relevant post-graduate qualification)
- Expertise in Structured Query Language (SQL) and database processing (ETL, stored procedures, large datasets)
- Experience in at least one of the following statistical packages: R (preferred), Python (data science toolkits, particularly Pandas, ggplot, Scikit Learn, Tensorflow, Keras), or Stata
- Experience working with relational databases (such as SQL Server), clinical or medical research, working with big data
- Statistical background (models, correlations, hypothesis), and database administration tools (migration, DB administration)
- Experience of working with real-life clinical databases /EMRs /registry data
- Strong in data analysis, interpretation, and visualization
- Natural Language Processing and use of regular expressions in R or Python, particularly in text-mining software (e.g. Python’s spaCy)
- Automating generation of regular reports, through R Markdown, Jupyter notebooks, or another report-generation software
- Data dictionaries and advanced documentation systems
Contract and Salary
Part-time and full-time roles are considered.
Starting salary is dependent on qualifications and your experience.
Immediate start is available.
Please send your CV with a covering letter summarising your suitability for the role to firstname.lastname@example.org. We look forward to hearing from you.