The primary purpose of this position is to analyze current data sets and identify supportive data sets for the development of new products using cutting edge tools and algorithms. The candidate must be passionate about supporting evidence-based decision making and driven to investigate patterns and relationships within data using systematic and scalable methods.
Position Duties and Responsibilities:
- Assume full responsibility for assigned projects and their design, development, delivery and evaluation.
- Assure on-going strategic and tactical knowledge and proficiency in all aspects of the current and potential industries served by Diaceutics.
- Use scalable methods to process, standardize, cleanse, and contextualize data sets.
- Construct mathematical models to understand relationships between different data fields and metrics.
- Identify significant patterns in the data.
- Construct algorithms for complete processes and run algorithms through AWS cloud services.
- Interpret molecular variants from clinical testing results and link molecular variants to disease through public and private reference data, including through database APIs.
- Drive innovative new products and features using external and internal data sources
- Champion data collection from all sources.
- Coordinate analytical activities with the broader activities within the Global Data team.
- Code with integrity. Demonstrate a commitment to documentation, review, and testing.
General Education and Experience:
- Education – Master’s or PhD Degree preferred, minimum of Bachelor’s Degree required
- Experience – 3-5 years of experience required.
- Computer and Software Knowledge and Skills – AWS cloud-based systems, including serverless architectures and efficient use of EC2 instances, Lambdas, SQL, Redshift, Elasticsearch, DynamoDB, Python, Java, Scala. D3 or bokeh a plus.
- Mathematical Modeling – manipulation and combination of sets, non-linear models, decision trees, Scikit Learn, PANDAS, Tensorflow, BigDL, Apache Spark, machine learning, neural networks, deep learning.
- Virtual Communication – demonstrated high-end expertise as user of video call technology and global teleconferencing.