Data Scientist

Key Skills

Data science techniques, Effective communication skills, Machine learning techniques, Management, Natural Language Processing (NLP), Python Programming, PyTorch, TensorFlow, XML-JSON

Job Description

SAIC, a leading provider of systems development and deployment, targeting and intelligence analysis, systems engineering and integration, and training capabilities and solutions for the Intelligence Community (IC), is seeking creative and dedicated professionals to fulfill their career goals and objectives, while delivering mission excellence on programs of national importance.

SAIC’s National Intelligence Community (NIC) Business Unit, USG Mission and Information Technology Division, is seeking a Data Scientist who will enable and grow existing automation efforts, add additional data streams, and drive forward our natural language processing efforts. The Data Scientist will focus on the business analytics, metrics collection, and analysis efforts. 

Responsibilities include:

• Designing and implementing advanced code and table configurations for complex data sets
• Compiling data analysis and conducting sophisticated analysis using deployed tools and natural language processing
• Producing ad hoc reports to answer questions
• Provide training to staff

Qualifications

Required Qualifications:

• Active TS/SCI with polygraph
• Bachelor's Degree (B.S.) in Computer Science, Software Engineering, Information Management Systems, or a related discipline. Note that years of experience can be substituted in lieu of degree
• Three (3) or more years of demonstrated experience in the following
  • Creating machine learning models that conduct binary or multi-class text classification in Python using standard machine learning (Scikit-learn) or deep learning models (TensorFlow or PyTorch)
  • Processing data holdings to extract topics that could be parsed to further illuminate areas of customer interest and collection priorities
  • Using Python natural language processing (NLP) packages such as Spacy, Gensim, or NLTK to analyze or process collections of written document to ascertain customer interest and priorities
  • Reviewing documentation and APIs of commonly-used NLP packages to choose the one with the best fit for a given NLP task and implement it
  • Performing pre-processing actions for text data sets for use in NLP projects (lemmatize, remove stop words, or use regular expressions to remove organization-specific stop phrases
  • Writing, maintaining, and customizing Python scripts that read and write text from various formats such as MS Word, PDF, or XML

Desired Qualifications:

• Demonstrated experience building semantic language models and search engines
• Demonstrated experience with developing data visualizations
• Demonstrated experience addressing procedural and administrative issues within the assigned problem set
• Demonstrated experience with web analytics processing, scraping, and procedures
• Demonstrated knowledge of national collection priority tagging system