DS Data Scientist
Summary
A data scientist supporting national security analytics for a government sponsor: analyzing large, complex data sets, applying statistical and machine learning methods (classification, clustering, anomaly detection), and participating in threat hunting. Core skills are coding, SQL, Hadoop, and statistics; requires an active TS/SCI clearance with polygraph. On-site in Chantilly, VA.
- Working with large, complex, and disparate data sets
- Designing and implementing innovative ways to analyze and exploit the Sponsor’s data holdings
- Researching and reporting on a wide variety of Sponsor inquiries
- Raising proactive inquiries to the Sponsor based on observations and proposed data analysis/exploitation
- Solving difficult, non-routine problems by applying advanced analytical methodologies, and improving analytic methodologies
- Developing custom searches
- Participating in threat hunting and/or developing advanced, novel detection mechanisms to counter malicious actors
- Thorough knowledge of appropriate analytic tools and methodologies in one or more of the following:
- Applied mathematics (e.g. probability and statistics, formal modeling, computational social sciences)
- Computer programming (e.g. programming languages, math/statistics packages, computer science, machine learning, scientific computing)
- Ability to code or script in one or more general programming language
- Experience with, and understanding of, algorithms for classification, regression, clustering, and anomaly detection
- Knowledge of relational databases, including SQL and large-scale distributed systems (e.g. Hadoop)
- Expertise with statistical data analysis (e.g. linear models, multivariate analysis, stochastic models, sampling methods)
- Demonstrated effectiveness in collecting information and accurately representing/visualizing it to non technical third parties
- Experience working in a mission environment and/or with many different types of data
- Familiarity with building MVP/Prototype data engineering pipelines to support novel analytics
- Experience in signature development, threat hunting, and/or threat modeling
- Background in computer network operations, particularly network defense and/or exploitation