Data Scientist & Data Engineering

TS/SCI and Poly is Required

McLean, VA

PROGRAM SUMMARY

We provide tactical data engineering solutions. We embed skilled Data Engineers, Data Scientists, and ETL Developers directly into intelligence analyst groups to be their go-to data wranglers. We develop new tools, code, and services to execute data engineering activities. Our engineers work to collect, process, and feed analytic tools, turning data into intelligence in response to immediate mission needs, with direct impact on real world situations. You will see your work used here on a daily basis, and you'll have the opportunity to support a variety of Sponsor mission organizations and mission partner organizations.

This is a time of development and growth on the program, with an increasing number of missions being supported. The work is high impact and important, and the customer moves quickly. The environment is fast-paced, flexible, and open to innovation - you'll have more latitude here in choosing how to achieve results than on many other projects. The customer cares more about what you can do as opposed to your years of experience, and work hours are typically quite flexible - roll up your sleeves, get things done, and no one cares much about the specific hours that you work. The work space itself is also quite nice, and there is an excellent cafeteria!

The tech stack on this team is rather huge and includes Python (Pandas, numpy, scipy, scikit-learn, standard libraries, etc.), Python packages that wrap Machine Learning (packages for NLP, Object Detection, etc.), Linux, AWS/C2S, Apache NiFi, Spark, pySpark, Hadoop, Kafka, ElasticSearch, Solr, Kibana, neo4J, MariaDB, Postgres, Docker, Puppet, and many others.

Work on this program takes place in McLean, VA and in various field offices throughout Northern VA (we cannot support remote work) and requires a TS/SCI + Polygraph clearance (acceptable to this customer).

ROLE SUMMARY

This is a Python on Linux Data Science / Data Engineering role in which you will support various missions over time, with assignments ranging from "fix this mission problem now" to building something that may take a couple of months to complete, and everything in between. You'll work with massive data sets, both structured and unstructured. The work can vary from providing short-term help on a mission issue, to deciding how to set up a data pipeline, to building data pipelines, to writing both ad-hoc and reusable ETL code, to querying and analyzing data in SQL or Graph databases, to flexing your data engineering and software development muscles to build new tools. You may also provide consulting and technical recommendations to other sub-teams on their approach to solving their particular mission problems. Each mission is different, and you'll likely work with a very wide variety of technologies. Overall, a strong problem-solving mindset is key to success in this role.

Required Skills

• Strong Python experience, including working with key Python Data Science packages (Pandas, numpy, scipy, scikit-learn), the Python standard libraries, and making requests to APIs from Python (FastAPI, etc.)
• Strong Linux / Linux command line experience, including being able to set up Data Science environments on Linux machines, installing software and patches, managing software environments, managing and modifying configuration files, fixing broken dependencies, and writing basic scripts in Bash or a similar shell
• Experience working within AWS environments
• Experience building data pipelines and conducting ETL
• Experience querying SQL databases
• Experience analyzing diverse file types (text, image, video, audio, and binary)

Desired Skills

Any of the following could be useful on the program:

• Experience querying Graph databases
• Experience working with geospatial tools and data sets
• Experience managing pipelines
• Familiarity with Python packages that wrap standard machine learning (NLP, object detection, etc.)
• Familiarity with Front-End development (such as with Plotly's Dash library for python)
• Experience working with Apache NiFi, Spark, pySpark, Hadoop, Kafka, ElasticSearch, Solr, Kibana, neo4J, MariaDB, Postgres, Docker, or Puppet