The company is looking to solve the problem of advancing state-of-the-art modeling and prediction capabilities in object detection robustness.
Requirements
- 5+ years of experience designing and implementing data curation techniques specifically those designed for imagery
- Experience with building and maintaining ETL pipelines and Kubeflow pipelines
- Experience with imagery data, overhead imagery (optical or Synthetic Aperture Radar (SAR)), and synthetic data generation and analysis
- Familiarity with machine and deep learning libraries such as Scikit-learn and PyTorch
- Proficiency with the Python programming language
- Experience with Git version control systems
- Familiarity with the Linux OS
Responsibilities
- Work in a cross-functional software development and product development team to build code to analyze data and execute the data analysis
- Create and simulate synthetic data to augment computer vision models where data is scarce
- Assess, transform, organize, and optimize data for use by machine learning algorithms
- Develop algorithms to efficiently process data, executed standardized analysis
- Support to writing Data Science related project proposals
- Engagement in solutioning sessions
- Drafting portions of the technical sections of a project proposal
Other
- Active TS/SCI clearance
- US Citizenship is required
- Prolonged periods sitting at a desk and working on a computer
- Must be able to lift up to 10-15 pounds at time
- Desire a fast-paced, collaborative, Agile environment
