We are currently seeking motivated and customer oriented Data Scientist to begin a rewarding and challenging career with SAIC.
Candidate will work with analysts to develop optimized analytics scripts, dashboards and applications for analyzing network traffic data residing in a big data platform. Support high velocity, volume, and variety data ingestion. Support data ingestion and cleansing tasks, as well as cell-level tagging. Migrate analytics to run as data is migrated to new platforms. Support the data standards and vocabulary for a data brokering service and the development of a data catalog including a data dictionary and index. Work in DevSecOps for the development of complex applications, data parsing, a data portal. Support the reporting of Metrics.
Works in cross-functional teams with data at all stages of the analysis lifecycle to derive actionable insight. Translates mission needs into an end-to-end analytical approach to achieve results. Performs the pre-analytics areas of data collection and understanding, data cleansing and integration, and data storage and retrieval. Determines the appropriate analytics based on the data and the desired outcomes, using techniques including feature detection, statistics, data mining, predictive modeling, machine learning, natural language processing, and business intelligence. Interprets the validity of results and communicates the meaning of those results. Has familiarity with data wrangling, analytics, and visualization software and programming languages, including analytics methods for big data. Follows a scientific approach to generate value from data, verifying results at each step. Candidate is expected to work at unclassified or classified secret SAIC facilities.
- Required Qualifications:
- BA and 5 years of experience
- Must have or be able to obtain a secret clearance
- Experience with network monitoring data
- Experience with Apache tools for big data platforms
- Familiarity with data storage such as HDFS, Relational DB such as Postgres, NoSQL databases
- Familiarity with Elasticsearch
- Experience with Kafka and cross-domain data feeds is desired