Data Scientist

About the role

Located in Chantilly, this Data Scientist (Subject Matter Expert) position works closely with the client’s technical lead to architect, deploy, and maintain fast‑turnaround capabilities for high‑priority collection efforts, applying AI/ML to diverse data types and supporting data engineering tasks within the customer’s AWS environment.

Responsibilities

• Work closely with the client’s technical lead to architect, deploy, and maintain multiple, fast‑turnaround capabilities used to perform various highly‑visible and high‑priority collection efforts.
• Strategically apply AI/ML to extract, format, and expose in indexed search tools relevant content such as raw text, multimedia (audio, image, video, document), tabular (CSV, Parquet, Avro) or nested (JSON, JSONL, XML), and other structured/unstructured data types.
• Provide Data Engineering support to include cleaning, modeling, and formatting data of unknown formats.
• Move data between different cloud storage environments for critical requests.
• Coordinate with multiple entities, including mission partners, to ensure capabilities and deliverables meet defined requirements and tradecraft needs.
• Create and maintain collection capabilities and deliverables within the Customer’s Amazon Web Services environment utilizing Customer approved AWS services.
• Validate collected data to ensure it meets data format requirements.
• Maintain all source code in Customer’s GitHub repository.
• Document all source code, including how to execute the code.
• Perform operations and maintenance on the collection capabilities and deliverables to adapt to changes in collection target, technologies, data formats, and naming conventions.

Requirements

• Demonstrates experience with Python.
• Demonstrates experience with geo‑spatial software and programming packages and data formats.
• Demonstrates experience creating and managing AWS resources, including provisioning EC2 instances, writing and deploying Lambda functions, creating and writing to S3, and managing authorization appropriately across resources with IAM policies.
• Demonstrates experience using GitHub.

Skills

• Demonstrates experience deploying AWS applications with AWS’s Cloud Development Kit (CDK). Ansible and Terraform are NOT a substitute for CDK.
• Demonstrates experience building and deploying containerized applications.
• Demonstrates experience building, programmatically working with and maintaining search engines such as ElasticSearch, Lucene, or AWS’s OpenSearch.
• Demonstrates experience creating, programmatically working with and maintaining SQL and NO‑SQL databases.
• Demonstrates experience with other non‑AWS cloud services such as, Google Cloud Platform, Microsoft Azure.

Qualifications

• Certification(s): AWS DevOps Engineer, Solutions Architect, or SysOps Administrator.