Merrifield, VA

Job Summary: Looking for a broadly talented Data Scientist with quantitative research skills to take an active role on our data analytics team. You will work on vast amounts of Drug Enforcement Agency (DEA) data to discover hidden information by applying modern statistical and ML/AI techniques. The main scripting languages used on this program are Python and some 'R'. The databases are MS SQL Server and Elastic Search is used again the data warehouses with Kibana, Tableau, or other BI and Visualization tools. This is a mature team that is high profile and charged with delivering solutions in Data Sciences enabling maximum leverage of the DEA master data. Your primary focus will be in applying data mining techniques, doing statistical analysis, and building high-quality prediction systems integrated with DEA programs and DEA data (e.g., structured, unstructured, and mixed datasets). You will also design and develop automatic scoring using machine learning techniques, build recommendation systems, and design and develop classifiers for feature extraction. This program is one in which pushing boundaries and innovation within the scope of the program is valued. There is a fully supported effort to develop and further ML/AI in the quest for 'making the data dance'. The Data Sciences group provides innovative algorithm development using various techniques to achieve desired insight or open eyes to new revealing results and possibilities. In addition to technical knowledge the team values the ability to collaborate and communicate with one another to ensure a highly productive, respectful, and harmonious work setting be it virtual or mixed of onsite and remote. At the present time, this role is remote however post covid-19 pandemic work is being done to possibly have a hybrid (remote/onsite) model. This is not confirmed at this time but is in the process of evaluating and planning with an eye on the current global health situation. Responsibilities: Work with large DEA data using descriptive statistics and data visualization tools
Create insights from existing DEA data, and drive the collection of new data and ways to address new data
Selecting features, building, and optimizing classifiers using machine learning techniques
Data mining using state-of-the art methods
Collaborate with clients and team members to understand and communicate results, and to put insights into operation
Enhancing data collection procedures to include information that is relevant for building analytical systems
Doing ad-hoc analysis and presenting results in a clear manner
Creating automated anomaly detection systems and constant tracking of performance
Work with other team members such as those focused on data warehousing, tools development, software development, DevOps, systems analysts, etc.
Design accurate and scalable prediction algorithms
Collaborate with engineering team to bring analytical prototypes to production
Generate actionable insights for business improvements Requirements: Must be able to work onsite in Merrifield, VA.
Bachelor’s degree in a quantitative social science or a STEM field
5+ years of professional experience in data science and analysis
5+ years working experience with Python, “R” or other scripting languages
5+ years database experience
ML concepts - Decision Trees and Random Forest Preferred Qualifications (but not required): Graduate degree in a quantitative social science or a STEM field highly desired
10+ years of professional experience in data science and analysis
10+ years working experience with Python, “R” or other scripting languages
5+ years database experience
Proficiency in using data query languages such as SQL, Hive, Pig, Pandas, MongoDB
Proficiency in big data modeling work: Hadoop, Pig, Scala, Spark
Excellent understanding of machine learning techniques and algorithms, such as k-NN, Naïve Bayes, SVM, Decision Forests, etc.
Substantial experience with statistics and the scientific method, and the ability to perform self-directed hypothesis-driven research
Experience with common data science toolkits, such as R, Weka, NumPy, MatLab, etc.
Experience with data modeling programming and software development, including Python, R, or other high-level language used in statistical computing
Experience or knowledge of ELK may be helpful
Good, applied statistics skills, such as distributions, statistical testing, regression, etc.
Ability to present to, communicate with, and collaborate well with non-technical people
Ability to communicate effectively both orally and in writing
Dedication to continued learning, be team dedicated, self-driven, quality minded, and customer-friendly Additional: Ability to obtain and maintain a DoD government secret (or higher) clearance
Must be able to pass a DEA “Suitability” review