Data Scientist (TS/SCI + Poly)

Description

The DarkStar Group, a GRVTY Company is seeking a Data Scientist with a TS/SCI + Poly clearance (applicable to this customer) to join one of our top projects in Tysons Corner, VA.  Below is an overview of the project, as well as information on our company, our benefits, and our $25,000 referral program.

THE PROJECT

The DarkStar Group's team is charged with taking commercial and academic innovation high-side, in domains of Artificial Intelligence / Machine Learning (AI / ML) such as Computer Vision (Image and Video Processing), Natural Language Processing (NLP), and Audio Modeling.  We also bring the best ideas, tools, and approaches in technology infrastructure (AWS, DevOps, etc.) to the IC.  The tech stack used is extremely broad - anything cutting edge in the commercial market, the open source community, or the academic research community is likely involved: and if something isn't being looked at yet, you can make that happen.

This effort supports ALL missions of the Intelligence Community, including cyber-related data science missions.  A seamless group of contractor and customer personnel work to create innovations that supply customer groups with the data sets, models, algorithms, software, and infrastructure they need to increase their mission success.  Management is hands off, gives the team the freedom to explore new approaches, and markets the best ideas and results to all the other IC customers.  

This project regularly needs various types of people - Data Scientists, Data / ETL Engineers, Analytic Software Engineers, Full Stack Developers, UI/UX Developers, and AWS/DevOps experts.  We're particularly interested in people with any of the following experience:

• developing AI / ML models (neural networks, tree based algorithms, etc.);
• conducting data analysis in the fields of Computer Vision, NLP, or audio signal processing;
• doing data ingest and ETL into sponsor environments; or
• building data-analytic software systems.

Work on this program takes place throughout the Reston/Herndon/Chantilly, VA area (we cannot support remote work) and requires a TS/SCI + Poly clearance (acceptable to this customer).

The Role

• Create and apply machine learning capabilities to enrich data. 
• Determine appropriate approaches to analyze data sets (including statistical analysis). 
• Maintain existing ML tools (e.g., v19 auto-tagging, citation analysis). 
• Develop and expand ML data science tools, such as NIPF v20, future auto-tagging, unsupervised clustering capability. 
• Develop and deploy ML tools to evaluate analytic tradecraft conformance or other text-based standards, such as confidence and probability. 
• Maintain code and model documentation sufficient to support design and code reviews; enable efficient deployment of code into operational systems; and address/diagnose issues stemming from code and model outputs. 
• Develop forecasting and modeling tools that offer diagnostic and predictive insight regarding IC mission performance and connection to other inputs and variables (e.g. resources, priorities). 

Required Skills

• Bachelor’s degree in a relevant field (Computer Science, Economics, Mathematics, Statistics, Computer Engineering, Electrical Engineering, Bioinformatics) or equivalent relevant experience. 
• 5+ years of data science experience and/or training in data science. 
• Extensive demonstrated skills and experience with developing and tuning AI/ML algorithms and implementing testing/validation approaches appropriate to available data and validation targets. 
• Advanced experience using Python and appropriate libraries/extensions (e.g., PyTorch, Cuda, SciKit-Learn) to code and test AI/ML algorithms. 
• Demonstrated experience in written and verbal communication on complex analytic methods and/or technologies to technical and non-technical audiences. 
• Extensive experience with natural language processing tools and techniques. 
• Advanced understanding of descriptive statistics, regression, and data labeling/classification models. 

Desired Skills (Optional)

• Advanced skills in data extraction, parsing, manipulation, and storage; quantitative and qualitative analyses based on the large volume of data from various IC databases 
• Demonstrated experience leading technical teams in a management or subject matter expert advisory capability. 
• Extensive experience conducting data extraction, parsing, manipulation, and analysis of large volumes of data from various IC databases. 
• Experience with data engineering techniques, especially for cloud-based data infrastructure and data lake environments. 
• Extensive experience developing custom scripts, queries, or visualizations to support analysis of IC data. 
• Expe