Applied Data Scientist
- Full-Time
- Mission Support
- Remote
Barbaricum is a rapidly growing government contractor providing leading-edge support to federal customers, with a particular focus on Defense and National Security mission sets. We leverage more than 15 years of support to stakeholders across the federal government, with established and growing capabilities across Intelligence, Analytics, Engineering, Mission Support, and Communications disciplines. Founded in 2008, our mission is to transform the way our customers approach constantly changing and complex problem sets by bringing to bear the latest in technology and the highest caliber of talent.
Headquartered in Washington, DC’s historic Dupont Circle neighborhood, Barbaricum also has a corporate presence in Tampa, FL and Dayton, OH, with team members across the United States and around the world. As a leader in our space, we partner with firms in the private sector, academic institutions, and industry associations with a goal of continually building our expertise and capabilities for the benefit of our employees and the customers we support. Through all of this, we have built a vibrant corporate culture diverse in expertise and perspectives with a focus on collaboration and innovation. Our teams are at the frontier of the Nation’s most complex and rewarding challenges. Join us.
Barbaricum is seeking an experienced Applied Data Scientist with hands-on coding experience to provide support for telemetry and maintenance analysis for a Marine Corps vehicle sustainment program. This program is focused on the direction, synchronization, and modernization of Condition Based Maintenance applications for the USMC, leveraging data science and predictive analytics to improve performance and reliability. This individual will work within the Advana Enterprise Platform to develop, consult, and apply analytical methodologies for disparate and unstructured datasets.
Responsibilities
- Design, configure, develop, test, and support data science solutions for a wide array of telemetry based USMC use cases, to include NLP and sensor-based algorithms.
- Leverage Large data sets encompassing 8+ years of historical data.
- Conduct complex data assessments to determine operational utility of proposed data sets in answering priority requirements.
- Discover links and connections in disparate datasets providing context to analysts.
- Interpret and analyze data using exploratory mathematic and statistical techniques based on the scientific method.
- Experiment against data points, provide information based on experiment results and provide previously undiscovered solutions to command data challenges.
- Coordinate with Data Engineers to build Data environments providing data identified by Data Analysts, Data Integrators, Knowledge Managers, and Intelligence Analysts.
- Coordinate research and analytic activities utilizing various data points (unstructured and structured) and employ programming to clean, massage, and organize the data.
- Develop and maintain data pipelines to ingest applicable data into AI/ML engines and tools.
Qualifications
- Active DoD Secret Clearance
- Bachelor's Degree in quantitative field such as Mathematics, Statistics, Electrical Engineering, Computer Science, or Operational Research (Master's preferred)
- 5+ years of practical, hands-on experience in building, training, and implementing algorithms for predictive modeling.
- 5+ years of data science and analysis experience, with demonstrated exposure to cloud architectures including, but not limited to, Databricks, MLFlow, and AWS S3.
- Hands-on experience with ML fields, e.g., natural language processing, computer vision, sensor-based algorithms, statistical learning theory
- Ability to take unstructured text and build tools to feed into predictive algorithms, moving effectively from NLP to predictive analytics.
- Ability to quickly and effectively pivot and re-work solutions when initial assumptions fail.
- Demonstrated experience and proficiency writing code in Python (Class and Functions), in addition to exposure to R.
- Experience handling terabyte-size datasets, diving into data to discover hidden patterns, using data visualization tools, and writing SQL queries and scripts.
- Experience writing and speaking about technical concepts to business, technical, and lay audiences and giving data-driven presentations.
Desired Qualifications
- Proficiency in SQL and noSQL databases
- Experience with SQLAlchemy, Flask, Streamlit, Dash, React, JavaScript, HTML/CSS
- Familiarity with Spark, GoLang, and Application Programming Interfaces (APIs)
- Knowledge of Continuous Integration / Continuous Development (CI/CD) practices
- Experience with Gitlab and Jira
