Responsibilities
Develop, train, evaluate, and improve machine learning and deep learning models using aerial imagery and geospatial datasets.
Design and conduct experiments to evaluate model architectures, training strategies, datasets, and other approaches to improve model performance.
Perform data exploration, preprocessing, and error analysis to identify data quality issues, model limitations, and opportunities for improvement.
Develop computer vision solutions for tasks such as segmentation, depth estimation, object detection, and image classification.
Apply established machine learning practices and technical judgment to solve defined problems with minimal guidance.
Collaborate with data scientists, engineers, product teams, and domain experts to develop effective machine learning solutions.
Contribute to reproducible training, evaluation, benchmarking, and model development workflows.
Communicate findings and technical decisions, contribute to documentation and knowledge sharing, and participate in technical reviews and design discussions.
Qualifications
Required Experience
2–4 years of hands-on experience in data science, machine learning, computer vision, or a related field.
Strong programming experience in Python, with experience using common data science and machine learning libraries.
Hands-on experience developing and training deep learning models using frameworks such as PyTorch, TensorFlow, or similar.
Understanding of fundamental machine learning concepts, including supervised learning, self-supervised learning, model evaluation, feature engineering and optimization.
Familiarity with computer vision concepts and techniques, such as instance and semantic segmentation, depth estimation, object detection, image classification, or related tasks.
Experience working with large datasets, including data preprocessing, dataset preparation, and exploratory data analysis.
Strong analytical and problem-solving skills with the ability to investigate complex model and data-related issues and develop appropriate solutions within a defined problem space.
Ability to design and execute experiments, interpret results, and clearly communicate findings and recommendations.
Familiarity with cloud platforms such as AWS and GPU-based model training environments.
Effective written and verbal communication skills and the ability to collaborate with cross-functional teams.
Familiarity with version control systems, such as Git, and collaborative software development practices.
Preferred Experience
Experience working with aerial, satellite, geospatial, or other large-scale imagery datasets.
Experience with modern deep learning architectures such as Vision Transformers, Foundation Models and CNNs.
Exposure to MLOps practices, including experiment tracking, model versioning, reproducible training pipelines, and model lifecycle management.
Experience with distributed or large-scale model training.
Familiarity with geospatial data formats, GIS concepts, or remote sensing applications.
Core Competencies
The successful candidate will demonstrate strength in the following competencies as well as which can be found here:
Drive & Follow Through – Takes initiative and turns ideas into action.
Adaptability in Uncertainty – Adjusts quickly and performs through change.
Customer-Centered Mindset – Puts customer needs at the center of decisions.
Judgment & Problem Solving – Makes sound decisions and solves problems effectively.
Role-Specific Expertise – Applies strong functional expertise to deliver results.
Results Accountability – Owns outcomes and delivers on commitments.
Work Prioritization & Execution – Focuses on priorities and delivers on time.
EEO Statement
This job description is not an exclusive or exhaustive list of all job functions that a workforce member in this position may be asked to perform. Duties and responsibilities can be changed, expanded, reduced, or delegated by management to meet the business needs of the company.
The compensation offered to the successful candidate will be based on a variety of factors, including but not limited to, the candidate’s work experience, education and licenses, work-related training, key skills, the core duties of the role and its associated responsibilities, additional benefits offered, and the location where the work will be performed.
Develop, train, evaluate, and improve machine learning and deep learning models using aerial imagery and geospatial datasets.
Design and conduct experiments to evaluate model architectures, training strategies, datasets, and other approaches to improve model performance.
Perform data exploration, preprocessing, and error analysis to identify data quality issues, model limitations, and opportunities for improvement.
Develop computer vision solutions for tasks such as segmentation, depth estimation, object detection, and image classification.
Apply established machine learning practices and technical judgment to solve defined problems with minimal guidance.
Collaborate with data scientists, engineers, product teams, and domain experts to develop effective machine learning solutions.
Contribute to reproducible training, evaluation, benchmarking, and model development workflows.
Communicate findings and technical decisions, contribute to documentation and knowledge sharing, and participate in technical reviews and design discussions.
Required Experience
2–4 years of hands-on experience in data science, machine learning, computer vision, or a related field.
Strong programming experience in Python, with experience using common data science and machine learning libraries.
Hands-on experience developing and training deep learning models using frameworks such as PyTorch, TensorFlow, or similar.
Understanding of fundamental machine learning concepts, including supervised learning, self-supervised learning, model evaluation, feature engineering and optimization.
Familiarity with computer vision concepts and techniques, such as instance and semantic segmentation, depth estimation, object detection, image classification, or related tasks.
Experience working with large datasets, including data preprocessing, dataset preparation, and exploratory data analysis.
Strong analytical and problem-solving skills with the ability to investigate complex model and data-related issues and develop appropriate solutions within a defined problem space.
Ability to design and execute experiments, interpret results, and clearly communicate findings and recommendations.
Familiarity with cloud platforms such as AWS and GPU-based model training environments.
Effective written and verbal communication skills and the ability to collaborate with cross-functional teams.
Familiarity with version control systems, such as Git, and collaborative software development practices.
Preferred Experience
Experience working with aerial, satellite, geospatial, or other large-scale imagery datasets.
Experience with modern deep learning architectures such as Vision Transformers, Foundation Models and CNNs.
Exposure to MLOps practices, including experiment tracking, model versioning, reproducible training pipelines, and model lifecycle management.
Experience with distributed or large-scale model training.
Familiarity with geospatial data formats, GIS concepts, or remote sensing applications.
Core Competencies
The successful candidate will demonstrate strength in the following competencies as well as which can be found here:
Drive & Follow Through – Takes initiative and turns ideas into action.
Adaptability in Uncertainty – Adjusts quickly and performs through change.
Customer-Centered Mindset – Puts customer needs at the center of decisions.
Judgment & Problem Solving – Makes sound decisions and solves problems effectively.
Role-Specific Expertise – Applies strong functional expertise to deliver results.
Results Accountability – Owns outcomes and delivers on commitments.
Work Prioritization & Execution – Focuses on priorities and delivers on time.
