SoSi Data Scientist in Reston, Virginia

Company Overview

For 25 years, clients in the private and public sectors have relied upon SOS International LLC (SOSi) for critical operations in the world’s most challenging environments. SOSi is privately held, was founded by its current ownership in 1989, maintains corporate headquarters in New York City, and specializes in providing logistics, construction, training, intelligence, and information technology solutions to the defense, diplomatic, intelligence and law enforcement communities.

All qualified applicants will receive consideration for employment and will not be discriminated against on the basis of race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability, or protected veteran status. SOSi takes affirmative action in support of its policy to advance employment of individuals who are minorities, women, protected veterans, and individuals with disabilities.

EXOVERA-160630-4470: Data Scientist

Job Category IT/Engineering

Duty Location U.S. - Virginia - Reston

Type of Position Full Time

Requisition Number EXOVERA-160630-4470


Exovera, an SOS International LLC (SOSi) company, is seeking a Data Scientist to join our team of media analysis professionals in our Reston office.

In this position, you will help develop linguistic and quantitative based scoring and analytics products that allow our media analysts to access and analyze collected traditional and social media data. Our engineering team is small, so this is an opportunity for the right candidate to apply original research and cutting edge techniques to design original products that have a high impact on our overall business goals.

The ideal candidate will have experience designing quantitative analytic products in both traditional and social media analysis space. He or she will have the ability to work independently to produce reports, design custom analytics and contribute to the production of interactive dashboards as outputs. Experience in data mining, computational linguistics, Natural Language Processing, Machine Learning and Predictive analytics is a must. Some experience developing solutions that utilize Elasticsearch, R, D3.js, Shiny, Java, Numpy etc. is also highly desirable.


• Create and apply models, and visualizations for News and Social Media analysis; such as, predictive analytics, narrative modeling, trending, etc.

• Develop solutions for back-end and front-end data enrichment, such as statistical topic, quote, and event extraction

• Retrieve, process and prepare a rich data variety of data sources such as social media, news, etc.

• Analyze and model structured data and implement algorithms to support analysis using advanced statistical and mathematical methods from statistics, machine learning, data mining, econometrics, and operations research

• Perform statistical Natural Language Processing to mine unstructured data, using methods such as document clustering, topic analysis, named entity recognition, document classification, and sentiment analysis

• Utilize a diverse array of technologies and tools as needed, to deliver insights, such as R, SAS, Python, Spark, Hadoop etc.

• Drive client engagements focused on Big Data and advanced business analytics, in diverse domains such as risk management, product development, marketing research, supply chain, public policy; communicate results and educate others through reports and presentations

• Perform exploratory data analysis, generate and test working hypotheses, and uncover interesting trends and relationships

• Master’s degree with a minimum of two years experience, or PhD in Computer Science, Statistics, Mathematics, Engineering, Econometrics, or related fields

• Strong mathematical background with strong knowledge in at least one of the following fields: statistics, data mining, machine learning, statistics, operations research, econometrics, natural language processing, and/or information retrieval

• Deep experience in extracting, cleaning, preparing and modeling data

• Experience with command-line scripting, data structures, and algorithms; ability to work in a Linux environment

• Proficiency in analysis (e.g. R, SAS, Matlab) packages

• Proficiency in programming languages (e.g. Python, Ruby, Java, Scala)



• Working conditions as normal for an office environment

• Requires periods of non-traditional hours including consecutive nights or weekends when necessary

• May require ability to lift/and or move objects or packages of up to 25 lbs