Job Title: Data Scientist
Department/Group: VENN
Reporting To: Senior Data Scientist
Years of Experience: 3+ years
Location: Mbarara
Travel Required: Up to 30%

At Raising The Village (RTV), we are dedicated to eradicating ultra-poverty in Sub-Saharan Africa. As a dynamic, rapidly growing international development organization, we’ve assembled a team of over 250 passionate individuals in Uganda, alongside an additional 17 professionals in North America and 15 in Rwanda. Together, we are committed to elevating communities out of ultra-poverty by implementing innovative solutions and leveraging advanced data analytics to drive impact.To date, our holistic approach has positively impacted over 1 million lives since 2012, and we’re poised to achieve even greater milestones, aiming to assist 1 million individuals annually by 2027. Our growth and success are fueled by the invaluable support of global partners who share our vision of sustainable change. Learn more about our impactful programs at www.raisingthevillage.org

The VENN department is the data and technology backbone of our organization, connecting advanced analytics, and custom software tools with field implementation to ensure data-informed decision-making at every level.

Job Description

The Data Scientist plays a pivotal role in designing, developing, and deploying a computer vision system that transforms how RTV assesses program compliance and household adoption across last-mile communities. The role sits within the Predictive Analytics / VENN department and is central to RTV's image based evaluation rollout, a key pillar of the broader WorkMate AI ecosystem. The Data Scientist will work closely with, Data Scientists, ML Engineers, the Data Engineer, the Software Engineering team, and field evaluation teams to deliver an objective, scalable, and field-deployable visual assessment tool that complements and enhances RTV's existing evaluation frameworks.

Key Responsibilities

• Research, design, and implement image classification and object detection models (including YOLO-based architectures) for automated adoption t across RTV program domains including agriculture, WASH and livestock adoption practices.
• Build and maintain end-to-end ML training, validation, and test pipelines ensuring model accuracy, reliability, and generalizability to field conditions in low-resource environments.
• Optimize models for edge deployment in environments with limited connectivity, including TensorFlow Lite integration for mobile and offline use cases.
• Design and manage image data collection protocols and annotation workflows to produce high-quality labeled datasets for compliance indicator categories across all program domains.
• Integrate image metadata and classification outputs with the RTV data warehouse (Databricks medallion architecture) for correlation with household progression and adoption metrics.
• Develop automated adoption classification outputs that map to RTV's binary and weighted adoption scoring frameworks and validate against AHS survey-based assessments.
• Conduct structured experiments to benchmark model performance across deployment contexts (Uganda, Rwanda, DRC), applying Weights & Biases for experiment tracking and reproducibility.
• Build and document RESTful APIs to expose model predictions to WorkMate and other consuming field applications.
• Maintain clear documentation of model architectures, preprocessing pipelines, evaluation metrics, and versioning practices for cross-functional collaboration.

Technical Requirements

• Bachelor's or Master's degree in Computer Science, Data Science, Statistics (Statistical computing )or a related quantitative field.
• 3+ years of hands-on experience in machine learning and computer vision, with a demonstrable portfolio of deployed models.
• Proficiency in:
  • Python (PyTorch or TensorFlow) for deep learning model development.
  • Object detection and image classification frameworks, particularly YOLO architectures (YOLOv8 or later).
  • Data annotation tools and active learning workflows for building labeled datasets.
  • Cloud platforms, specifically AWS, for model training, storage, and deployment.
  • SQL and familiarity with data warehouse environments (Databricks preferred) for integrating model outputs with structured household data.
  • Model deployment and MLOps practices, including CI/CD pipelines and experiment tracking with Weights & Biases or equivalent.
  • Edge deployment optimization (TensorFlow Lite, ONNX) for low-connectivity field environments.
• Experience building and documenting RESTful APIs to expose model predictions to consuming applications.
• Familiarity with mobile data collection platforms (SurveyCTO, ArcGIS, Custom APPs) and field data workflows in development or humanitarian contexts is an asset.

Personal Attributes

• Deep commitment to applying data science for social impact and poverty alleviation.
• Strong analytical and problem-solving mindset with attention to field-level constraints and practical deployment realities.
• Ability to communicate complex model outputs to non-technical stakeholders including field officers and program managers.
• Collaborative team player who thrives in a fast-paced, mission-driven environment with multiple concurrent workstreams.
• High degree of independence, initiative, and commitment to integrity and innovation.

• Research, design, and implement image classification and object detection models (including YOLO-based architectures) for automated adoption t across RTV program domains including agriculture, WASH and livestock adoption practices.
• Build and maintain end-to-end ML training, validation, and test pipelines ensuring model accuracy, reliability, and generalizability to field conditions in low-resource environments.
• Optimize models for edge deployment in environments with limited connectivity, including TensorFlow Lite integration for mobile and offline use cases.
• Design and manage image data collection protocols and annotation workflows to produce high-quality labeled datasets for compliance indicator categories across all program domains.
• Integrate image metadata and classification outputs with the RTV data warehouse (Databricks medallion architecture) for correlation with household progression and adoption metrics.
• Develop automated adoption classification outputs that map to RTV's binary and weighted adoption scoring frameworks and validate against AHS survey-based assessments.
• Conduct structured experiments to benchmark model performance across deployment contexts (Uganda, Rwanda, DRC), applying Weights & Biases for experiment tracking and reproducibility.
• Build and document RESTful APIs to expose model predictions to WorkMate and other consuming field applications.
• Maintain clear documentation of model architectures, preprocessing pipelines, evaluation metrics, and versioning practices for cross-functional collaboration.

• Python (PyTorch or TensorFlow) for deep learning model development.
• Object detection and image classification frameworks, particularly YOLO architectures (YOLOv8 or later).
• Data annotation tools and active learning workflows for building labeled datasets.
• Cloud platforms, specifically AWS, for model training, storage, and deployment.
• SQL and familiarity with data warehouse environments (Databricks preferred) for integrating model outputs with structured household data.
• Model deployment and MLOps practices, including CI/CD pipelines and experiment tracking with Weights & Biases or equivalent.
• Edge deployment optimization (TensorFlow Lite, ONNX) for low-connectivity field environments.
• Experience building and documenting RESTful APIs to expose model predictions to consuming applications.
• Familiarity with mobile data collection platforms (SurveyCTO, ArcGIS, Custom APPs) and field data workflows in development or humanitarian contexts is an asset.

• Bachelor's or Master's degree in Computer Science, Data Science, Statistics (Statistical computing )or a related quantitative field.
• 3+ years of hands-on experience in machine learning and computer vision, with a demonstrable portfolio of deployed models.
• Proficiency in:
  • Python (PyTorch or TensorFlow) for deep learning model development.
  • Object detection and image classification frameworks, particularly YOLO architectures (YOLOv8 or later).
  • Data annotation tools and active learning workflows for building labeled datasets.
  • Cloud platforms, specifically AWS, for model training, storage, and deployment.
  • SQL and familiarity with data warehouse environments (Databricks preferred) for integrating model outputs with structured household data.
  • Model deployment and MLOps practices, including CI/CD pipelines and experiment tracking with Weights & Biases or equivalent.
  • Edge deployment optimization (TensorFlow Lite, ONNX) for low-connectivity field environments.
• Experience building and documenting RESTful APIs to expose model predictions to consuming applications.
• Familiarity with mobile data collection platforms (SurveyCTO, ArcGIS, Custom APPs) and field data workflows in development or humanitarian contexts is an asset.