Data Scientist (Senior)
About Discovery
Discoverys core purpose is to make people healthier and to enhance and protect their lives. We seek out and invest in exceptional individuals who understand and support our core purpose, and whose own values align with those of Discovery. Our fast-paced and dynamic environment enables smart, self-driven people to be their best. As global thought leaders, Discovery is passionate about innovating in order to not only achieve financial success, but to ignite positive and meaningful change within our society.
About Discovery Insure
Discovery Insure is committed to creating a nation of great drivers and building better businesses through our innovative Shared-value Insurance model. Discovery Insure is South Africas fastest growing short-term insurance company with comprehensive products that provide protection against current and emerging risks facing clients in the motor, home and business insurance sectors.
Vitality Drive, an internationally-recognised and award-winning programme, is a key differentiator in the market that incentivises and rewards clients for driving well. The Vitality Drive programme has been scaled to local and international markets which now include Europe and the Middle East.
The company employs over 1 000 people who are committed to putting our customers and financial advisers first by providing unique and innovative solutions and cover.
Key Purpose
Maintain and develop the VitalityDrive scoring platform in AWS. To analyze large amounts of data to provide core business value and key insights and enhance business processes that rely on large amounts of data.
Areas of responsibility may include but not limited to
- Design, build, and maintain sophisticated production systems in AWS to ensure the system's scalability, reliability, and efficiency.
- Write and test high quality Python code that will run in a production environment. Familiarity with standard Python libraries.
- Monitor, troubleshoot, and resolve issues in our DevOps architecture, implementing preventative measures to reduce recurrence.
- Develop and implement data analytics and machine learning applications to optimize our systems and inform decision-making, eg. better detect and understand driving actions, driver intent, forecasting driver behavior.
- Document and manage all system operations to maintain transparency and easy reference for team members.
- Building models and developing algorithms to support new key initiatives, eg. better detect and understand driving actions, driver intent, forecasting driver behavior
- Data mining and cleaning
- Interpret and disseminate information via reports
- Researching and prototyping new technologies and methods that are relevant to the teams initiatives
- Providing business stake holders with relevant telematics data and findings in a useable format
- Comfortable working in Linux or MacOS environment
- Self-starter
- Optimistic change the world mentality
- Fixer attitude
- Drive to learn new skills and concepts
- Able to handle multiple complex projects simultaneously
- Programming experience in Python (preferred)
- Familiarity with continuous integration/continuous deployment (CI/CD), infrastructure-as-code (IaC), and other DevOps principles.
- Visualization tools and packages (eg. Seaborn, dash, plot.ly)
- Working knowledge of SQL
- Prior experience in data science, with a focus on analytics and machine learning application development.
- Familiarity with machine learning packages i.e. Tensor flow, Keras, FastAI
- GIS experience is advantageous
- Understanding of statistics and familiarity with statistical computing packages (eg. Scipy, numpy)
- Modern machine learning techniques, in particular working time series data, device data and natural language processing
- Algorithm analysis and code optimization
- Understanding of techniques required to work with extremely large datasets (larger than RAM)
- Ability to work with both structured and unstructured data, and ability to combine data from diverse sources
- Experience with the Python data science stack is advantageous (numpy, pandas, jupyter, scipy, etc)
- Matric
- Masters or Honours in one of the following fields: Computer Science, Applied Mathematics, Engineering, Physics, or similar.
- Solid experience (3+ years) in a Data Science / DevOps role, with demonstrated skills in Linux and the AWS ecosystem 2+ years Research experience ESS
- Strong statistics and analytical skills
- Prior programming experience required
The Companys approved Employment Equity Plan and Targets will be considered as part of the recruitment process. As an Equal Opportunities employer, we actively encourage and welcome people with various disabilities to apply.
