Senior Data Scientist, MNO Data

About GiveDirectly

GiveDirectly has delivered more than $1B in cash directly to 2+ million people living in poverty and crisis across 15 countries. We’re growing fast and expect to hit $1B in revenue in 2026 with significant growth forecast for 2027.

About this role

GiveDirectly works with Mobile Network Operators (MNO) to infer residence location from their data records to help target the poorest households and support emergency responses. We are hiring a Senior Data Scientist to progress this work on location inference from MNO data and make it repeatable.

Your job is to improve and extend our library of method templates, adapt them to each new operator and setting, and design new elements when an intervention requires it. You’ll assess what can be inferred from a given operator’s data, specify the analysis clearly enough for their data engineers to implement, then test it with them remotely or on site. You’ll support introductory meetings with MNOs and inform the work of data privacy and cybersecurity teams.

Reports to: Senior Product Manager - MNO data

Level: Senior Manager

Location: Remote, with substantial international travel (25-50% of time depending on emergencies). Hiring prioritized in: Cameroon, Canada, Colombia, DRC, Germany, Ghana, Kenya, Malawi, Mozambique, Netherlands, Nigeria, Poland, Portugal, Rwanda, South Africa, Spain, Turkey, Uganda, United Kingdom, and United States.

What you’ll do:

• Improve and extend analytical method templates for establishing where people live from MNO data, and design novel methods when an intervention requires it
• Support technical conversations with operators, bringing clarity on data needs and steering discussions toward workable technical designs
• Assess information that can be inferred from each operator’s data given data types and sparsity
• Write tests and method specifications for MNO data engineers to implement: steps, parameters, pseudocode, validation criteria
• Guide operator engineering teams through implementation, in writing and in person
• Run in-country workshops with operators to support new analyses and tune parameters based on statistical tests
• Feed every new analytical and implementation element back into standard templates
• Design for privacy from the start, using aggregation, minimization, and privacy-enhancing technologies such as private set intersection or homomorphic encryption
• Protect confidentiality and improve internal data security processes
• Build internal training material so technical and non-technical teams understand strengths and limits of this data source

What you’ll bring:

• Exceptional alignment with GiveDirectly Values and active demonstration of core competencies: emotional intelligence, problem solving, project management, follow-through, and fostering inclusivity
• Strong mathematical modeling, machine learning and statistics
• Deep comfort with spatio-temporal data: temporal filtering, GIS, probability distributions, combinatorial reasoning, and working with sparse, irregular observations
• Direct experience with Call Detail Records (CDRs) or latching data is a strong plus; comparable experience with mobility, transport, sensor or remote-sensing data counts
• Ability to reason without ground truth
• Pragmatism about the trade-off between accuracy and implementability
• Excellent communication and relationship-building skills; ability to explain methods and limitations to multiple audiences
• Experience writing technical specifications that other teams implemented
• Able to read and review SQL and Python written by others; writing production-quality code yourself is welcome but not required
• Commitment to privacy by design as foundational value; familiarity with privacy-enhancing technologies (private set intersection, secure multi-party computation, homomorphic encryption) is a strong plus
• Commitment to confidentiality
• Experience designing training material that changed how non-specialist colleagues used a data source
• Comfort in fast-moving contexts where the brief may shift
• Comfortable with travel to fragile and post-disaster contexts
• Language Requirement: English
• Language Preferences: French, Portuguese, Swahili or Spanish

Additional desirable experience: poverty modeling; familiarity with survey data and survey instruments; experience inside a mobile network operator or working closely with one; open-source contributions in the mobility estimation space