Maisha Meds is an organization dedicated to improving health care in Africa. We began full-time operations in 2017 and over the past few years has grown to support over 3million patient encounters annually across Kenya, Tanzania, Uganda, Nigeria, and Zambia with our suite of software products. We are building the financial and technology infrastructure to enable global health funders to pay for health outcomes at the last mile, with a focus on malaria case management (and results from a RCT with UC Berkeley due out later this year), injectable contraceptives, prenatal care, HIV pre-exposure prophylaxis, and COVID testing and vaccination.
About the Role
- Maisha Meds is seeking a mid-career data scientist with machine learning and statistics experience to join our data team. This role will focus on automating and scaling data cleaning and validation workflows, implementing machine learning features within an Android application, and contributing to the development of new data products.
- You’ll work on deploying real-world ML solutions in a complex environment,and collaborating closely with the product and engineering teams. Example projects may include building models for sales and stock-out forecasting, developing intelligent in-app features, and improving how we process and analyze large-scale health and retail datasets.
- This is a hands-on, highly collaborative role in a flexible, mission-driven environment—ideal for someone who enjoys applying machine learning to practical problems and enhancing real-world systems through data science.
Skills & Qualifications
Machine Learning & Data Science
- Design and implement end-to-end machine learning models using Python and relevant libraries, prioritizing production readiness and scalability
- Develop forecasting, time-series, and anomaly detection models
- Deploy models in resource-constrained environments like Android devices or lightweight back-end systems
- Build and maintain machine learning workflows, including data cleaning, feature engineering, and validation pipelines
- Evaluate model performance of off-the-shelf LLM and OCR tools, and provide recommendations for improvements
- Handle large, messy, or incomplete datasets from multiple sources to generate reliable insights
- Use data tools such as AWS, Terraform, dbt, Rivery, and Looker to support data infrastructure and workflows
- Proficiency in statistical methods and evaluating machine learning models
Collaboration & Technical Leadership
- Works well across teams, including product, engineering, and business development
- Provides technical leadership through activities like code reviews, architecture planning, and troubleshooting
- Communicates clearly and documents work effectively, especially when collaborating with cross-functional or multicultural teams
- Takes initiative to identify patterns, define problems, and propose actionable solutions
Education & Domain Knowledge
- Degree in Computer Science, Engineering, Statistics, or a related field is a plus, but not required
- Familiarity with pharmaceuticals, healthcare systems, or health-related data is a plus
Method of Application
Signup to view application details.
Signup Now
