Mission Focus: As a Data Scientist, you will contribute to a program advancing state-of-the-art modeling and prediction capabilities focused on object detection robustness. Working within a cross-functional team and reporting to a technical lead, you will operate across the machine learning development lifecycle, from data curation and synthetic data generation to model training, evaluation, and delivery.
Our delivery teams follow SAFe Agile practices, embrace the Ops ethos (DataOps/DevSecOps/MLOps) to "automate-first," and leverage modern tech stacks. This position requires a mid-to-senior level of experience, a passion for mission support, and a strong desire to solve our customers' hardest technical and data challenges.
Clearance: Active TS Clearance with ability to obtain TS/SCI. US Citizenship is required.
Location/Flexibility: Herndon, VA with remote flexibility. Must be local to the DC Metro area.
Responsibilities- Curate, transform, and optimize imagery data, including optical, Synthetic Aperture Radar (SAR), and synthetic data, for use by machine learning algorithms
- Design and maintain data conversion and ETL pipelines to prepare customer data for model training
- Generate and analyze synthetic data to augment computer vision models where real-world data is scarce
- Train, evaluate, and optimize deep neural network models on overhead imagery, including hyperparameter tuning and performance analysis
- Perform exploratory data analysis, feature engineering, and preprocessing to improve model performance
- Develop and visualize explainable AI metrics and model performance indicators
- Incorporate research and development outputs into the operational code base
- Communicate analytic findings to both technical and non-technical stakeholders
- Contribute to solutioning sessions and technical sections of project proposals
Required Qualifications- 5+ years of experience in data science, machine learning, or a related field
- Hands-on experience with data curation techniques for overhead imagery (optical or SAR) and computer vision model development
- Experience building and maintaining ETL or data processing pipelines
- Proficiency in Python and familiarity with machine learning and deep learning libraries such as PyTorch
- Experience with Git-based version control systems
- Proficiency working in the Linux operating system
- Strong analytical and problem-solving skills
- Ability to work in a fast-paced, collaborative, Agile environment
- Eligibility to work in classified environments and hold required security clearances
Preferred Qualifications- Experience with synthetic data generation and analysis for computer vision applications
- Experience with cloud-based or distributed computing platforms
- Experience deploying models into production and supporting ongoing operations and maintenance
- Experience communicating technical results to non-technical audiences or contributing to customer-facing deliverables
- Awareness of emerging data science, AI/ML, and big-data technologies relevant to national security missions
- Experience contributing to technical proposals
#JT
