Data Scientist - Senior

Job Type: Full- Time

Workplace Type: Onsite in Reston, VA

Clearance: TS/SCI and willing to take a CI Polygraph

Must be a U.S. Citizen

Benefits: Medical, dental, and vision coverage, 401k matching, generous PTO, paid holidays, professional training opportunities, and even pet insurance to ensure your furry friends are cared for too.

Job Summary

Castalia Systems is seeking a Data Scientist - Senior in the Reston, VA to provide Systems Engineering and Technical Assistance (SETA) for DIA’s CI/HUMINT efforts.

Roles and Responsibilities

A qualified candidate will perform the following duties and responsibilities, but are not limited to:

• Conducts data analytics, data engineering, data mining, exploratory analysis, predictive analysis, and statistical analysis.
• Utilizes scientific techniques to correlate data into graphical, written, visual, and verbal narrative products which enable informed analytic decision making.
• Able to proactively retrieve information from multiple sources, analyzes for better understanding of data and builds AI tools that automate organizational processes.
• Typical duties include:
  • creating various ML-based tools and/or processes (e.g. recommendation engines or automated lead scoring systems)
  • Statical Analysis
  • Applying advanced data mining techniques
  • Build high-quality prediction systems
• Other associated skillsets:
  • Data visualization and use of graphical applications to include MS Office (Power B) and Tableau.
  • Major data science languages such as R and Python
  • Managing and merging of disparate data sources, preferably using R, Python, or SQL
  • Data mining algorithms
  • Large data as it applies to multi-INT analytics, ML, and automated predictive analysis.

Required Qualifications:

• 10+ years of experience and a MA/MS degree

Desired Qualifications (Highly requested, but not mandatory):

• Be very comfortable using standard data science libraries including Keras, Pandas, and Scikit-Learn
• Have a solid understanding of classical NLP principles and concepts including lemmas, tokenization, and general text processing
• Be proficient preprocessing text using regular expressions, NLTK, SpaCy
• Have demonstrated experience using Python visualization libraries including Dash, Seaborn, or Plotly
• Possess some experience with the following:
  • OCR libraries
  • Data acquisition from PDF’s and handwritten notes
  • Web scraping (REST SOAP, BeautifulSoup)
  • Automation tools and methodologies.

Physical Requirements/Work Environment

• Normal office environment.

Travel

Less than 5%.

Company Description