Seeking an experienced Data Scientist with a history of analyzing complex systems to build predicative models and put the models into production. This individual will work to enhance AIA protection, detection and response to cyber security threats by: building/optimizing threat hunting use cases and search for new threat hunting use cases. Including machine learning where applicable. This individual will work alongside incident responders, engineers, analyst, data scientist, and other stake holders to achieve these goals. Roles and Responsibilities Work with stakeholders in technology risk to identify risks within data and develop models to be put into production that protect against those risks
Mine and analyse data from technology risk data to provide actionable insights
Identify and provide solutions for deficiencies in the data
Protect against cyber security threats by modelling them and ensure those models are put into production
Run ad hoc analysis on technology risk data
Examine the effectiveness of current use cases
Develop new cybersecurity use cases and optimize existing workstreams
Able to use data to support arguments
Develop ML models from design to production
Able to visualize data and present insights to stakeholders
Minimum Job Requirements
- Strong analytics background with an attention to detail.
- History of taking projects from data discovery, to actionable insights/predictive models, to production.
- Comfortable working with messy data, especially security logs.
- Familiarity with SIEM systems is preferred.
- Familiarity with ML models and experience developing ML models into a production system. Examples include: Random Forest, Deep Learning, clustering, etc.
- Experience with UEBA, lateral movement detectors and others is preferred.
- Knowledgeable about technology risk and cyber security in particular strongly preferred.
- Experience developing dashboards/reports in Tableau, Power BI or similar tool.
- Experience working in a cloud environment.
- Excellent communication skills and presentation skills.
- Must have a minimum of 5 years' experience in IT infrastructure, distributed computing, cloud based computing or similar.
- Master's or higher in physics, mathematics, computer science, economics or other quantitative field.
- Ability to script tasks and investigate data with Python or R.
- Able to write script using Spark, PySpark, etc.
- Able to run SQL queries.
- Experience with graph databases is preferred.
- Ability to optimize workflows for ML, databases, reporting is preferred.
- Experience with API calls.
- Comfortable working with large datasets, 100+ TB.
Job Segment: Scientific, Database, Computer Science, Cloud, SQL, Engineering, Technology