Data Scientist

About the role

The successful candidate will work to design and build large dataset Artificial Intelligence, Machine Learning and Data Analysis tools, and solutions. This position is on-site 4 days a week at our USPS customer site in Arlington, VA.

Responsibilities

• Work independently and within teams to use the necessary data extraction, manipulation, and aggregation techniques to prepare, clean, normalize, and validate data to complete varied projects and tasks.
• Research, design, and develop visualization solutions using a range of methods which support investigative and audit products.
• Design experiments, tests hypotheses, and build scalable models using data science and artificial intelligence (e.g. machine learning) methods.
• Lead artificial intelligence activities such as natural language processing, predictive analytics, and machine learning model development, training, evaluation, testing, refinement, deployment, and maintenance.
• Translate complex technical findings into an easily understood narrative. Prepare comprehensive documentation for requirements, test plans, user manuals, technical diagrams, and training materials.
• Provide advice on issues affecting projects, such as data access, quality, storage, and other related needs.
• Contribute to and present training and conference materials to large audiences.
• Independently perform comprehensive and efficient data collection and analysis of a variety of data sources to develop trends, descriptive statistics, or other insights.
• Use expert level knowledge to identify and develop sources of information from structured and unstructured data, criminal intelligence databases, public information sources, internal Postal Service databases, reference manuals, and audit and law enforcement reports.
• Develop substantial knowledge of database applications and environments and share expertise with coworkers in support of agency goals and objectives.
• Perform analysis of data for Extraction, Transformation, and Load (ETL) strategies, pattern recognition, and application of analytical tools.
• Review, analyze, and modify existing products including coding, debugging, testing, and documenting.
• Assist with training and conference development which may include presentations to large audiences.
• Facilitate between business owners and end-users who need to communicate with database administrators and traditional IT support staff.
• Ensure that quality/security guidelines are followed.
• Cook with identify and develop sources of information from structured and unstructured data, criminal intelligence databases, public information sources, internal Postal Service databases, reference manuals, and audit and law enforcement reports.
• Understand the concepts supporting relational databases, data warehousing, data governance, data access, data quality and related areas.
• Understand and follow a software development lifecycle (analysis, design, development, coding, testing, debugging, and documenting).

Requirements

• 5+ years' experience and skill writing coding languages (such as SQL, Python, R, and Java Scripts).
• 3+ years' experience working with projects involving machine learning, natural language processing, robotics process automation, artificial intelligence, text and/or data mining, as well as statistical and mathematical methods.
• At least 1 years of experience working with AWS or Azure services such as Databricks, Data Factory, and Data Lake.
• Experience with Azure DevOps and/or GitHub to support continuous integration and delivery pipelines, and operate within Agile frameworks to iteratively deliver high-quality data products, machine learning models, and artificial intelligence solutions.
• Develop, manage, and optimize automated data pipelines to ensure data integrity, support reliable analytics workflows, and enable effective collaboration across teams.
• Integrate disparate and diverse data sources-including flat files, relational databases, and external systems-using techniques such as JDBC/ODBC connections, REST APIs, and web-scraping methods to support robust analytics and data-driven decision-making.
• Understand the concepts supporting relational databases, data warehousing, data governance, data access, data quality and related areas.
• Knowledge of ODBC connection strings, and other external data source connection protocols.
• Expert proficiency in common data science tools, including scripted languages (such as SQL, Python, R, and Java Scripts), Integrated Development Environment and analytics platforms, open-source solutions, commercial off-the-shelf tools and hardware-based capabilities to support the data analytic development process and creating models, dashboards, and reports.
• Knowledge and experience using advanced analytic techniques such as machine learning, natural language processing, robotics process automation, artificial intelligence, text and/or data mining, and statistical and mathematical methods.
• Knowledge and experience using business intelligence applications and reporting technologies/methodologies including Data Analytics Expressions (DAX), data Mash-up(M), and Microsoft Power Platform (e.g., Power BI, Power Apps, Power Automate, etc.).
• Knowledge and experience using cloud computing platforms such as Azure.
• Knowledge and experience with relational databases and structured query language (SQL).
• Specialized experience working with programming languages (e.g., Python), business intelligence tools (e.g., Power BI), and analytics platforms (e.g., Databricks).
• Knowledge and experience in the law enforcement and/or audit industry.
• Experience using PySpark/PySpark SQL to process, transform, and analyze large-scale datasets.

Qualifications

• Bachelor's degree in Computer Science, Information Technology, Data Analytics, or related field.

Skills

• Specialized experience working with programming languages (e.g., Python), business intelligence tools (e.g., Power BI), and analytics platforms (e.g., Databricks).
• Knowledge and experience in the law enforcement and/or audit industry.
• Experience using PySpark/PySpark SQL to process, transform, and analyze large-scale datasets.

Benefits

MDW offers a competitive and comprehensive benefits and compensation package for our employees, including but not limited to:

• Health
• Dental
• Vision
• Group Life Insurance/Long Term Disability/Short Term Disability
• Retail/401(k)
• Flexible Leave Policy

Pay

TBD

Schedule

On-site 4 days a week at our USPS customer site in Arlington, VA.