Media Analyst Data ScientistDepartment: FederalEmployment Type: Full TimeLocation: McLean, VADescriptionOrbis is seeking a Media Analyst for a mission critical customer in the Intelligence Community. This is a multi-year project with growing potential, on which the Consultant will have the opportunity to demonstrate intellectual agility by exploring and leading cutting-edge data research design, data collection, and data analysis for a client in the US Intelligence Community, all centered around media analysis. This project features the opportunity to interact with a wide range of key stakeholders, including those at senior levels. This is an exciting opportunity for an intellectually curious, energetic data consultant to work autonomously on a project with real impact to help our client operate and develop ways of better meeting the needs of its customers. Key Responsibilities
- Demonstrated experience developing solutions with Python
- Demonstrated experience working with regular expressions
- Demonstrated experience with Natural Language Processing (NLP) /text processing in one or more of the following: text preprocessing and cleaning for downstream NLP tasks, information extraction, Named Entity Recognition (NER), identity matching, text normalization, automatic summarization, NLP evaluation, machine translation, machine transliteration, document exploitation pipelines, multilingual computing, ontology management, or computational lexicography
- Demonstrated experience with Exploratory Data Analysis (EDA) using Jupyter or similar notebooks.
- Demonstrated experience developing code with Visual Studio Code or similar Integrated Development Environment (IDE).
- Demonstrated experience with version control, e.g. git
- Demonstrated experience writing unit test frameworks such as pytest, junit, xunit, etc.
- Familiarity with/knowledge of Measures of Performance/Effectiveness
Skills, Knowledge and Expertise
- A Bachelor's degree is required for this position.
- Minimum of 5 years' experience in a consulting role in the IC.
- Demonstrated experience using PySpark and/or DataBricks
- Demonstrated experience with Python package deployment
- Demonstrated experience with data labeling, with solutions such as Doccano, Label Studio, or other equivalent
- Demonstrated experience developing solutions with SQL
- Demonstrated experience with SpaCy
- Demonstrated experience with Skweak/Snorkel.
- Demonstrated experience with task management software such as JIRA
- Demonstrated experience building discriminative classifiers for text data
- Familiarity with one or more foreign languages
- Prolonged periods of sitting at a desk and working on a computer.
- Routine video conference and/or in-person meetings.
- Ability to attend planned meetings within the Washington Metro Area region.