[Hiring] Machine Learning consultant @International Rescue Committee

Role Description

The International Rescue Committee (IRC) responds to the world's worst humanitarian crises, helping to restore health, safety, education, economic wellbeing, and power to people devastated by conflict and disaster. This consultancy is scoped to deliver both workstreams as discrete Phase 1 outputs of the IRC's broader ML for Programmes initiative.

• Role: Machine Learning Consultant – Data Science for Programmes
• Location: Remote
• Estimated Level of Effort: 42 days

Objectives

• Apply unsupervised machine learning (clustering) to client and population data from [Country A] to produce a needs assessment grounded in empirically-derived population segments.
• Conduct a methodological assessment and attempt at applying Multilevel Regression and Post-stratification (MRP) techniques to estimate needs in areas with sparse or uneven data coverage.
• Conduct a data feasibility assessment across candidate programme datasets in [Country B] to identify the most suitable pilot for predictive modelling.
• Produce a methodological guide for IRC Regional Measurement Advisers (RMAs) drawing on both workstreams.
• Build, validate, and document a first predictive model for the selected programme.

Qualifications

• Advanced degree (Master's or PhD) in economics, data science, statistics, computer science, or a related quantitative field, or equivalent professional experience.
• Demonstrated experience applying clustering and predictive modelling techniques to real-world datasets.
• Proficiency in R or Python (required); experience with Databricks is an advantage.
• Proven experience working with messy, incomplete, or administratively-generated data.
• Experience with MRP or similar small-area estimation techniques is desirable.
• Familiarity with the humanitarian or international development sector.
• Strong technical writing skills and the ability to translate analytical findings for non-specialist audiences.

Requirements

• Review available datasets for quality, completeness, and suitability for clustering.
• Conduct necessary data cleaning and structuring.
• Apply an appropriate clustering algorithm to identify distinct population segments.
• Produce a written needs assessment report interpreting the cluster outputs in programmatic terms.
• Review candidate programme datasets for suitability for predictive modelling.
• Build a predictive model using historical programme data.
• Translate the validated model into a lightweight operational tool.
• Produce a practical methodological guide for IRC Regional Measurement Advisers.

Deliverables and Timeline

• Data assessment note (Workstream A) - Weeks 1–2, Est days: 3
• Data cleaning and preparation (Workstream A) - Weeks 2–5, Est days: 7
• Clustering analysis and MRP assessment (Workstream A) - Weeks 5–9, Est days: 8
• Needs assessment report, final (Workstream A) - Weeks 9–12, Est days: 5
• Data feasibility assessment note (Workstream B) - Weeks 2–4, Est days: 3
• Model development and validation (Workstream B) - Weeks 8–14, Est days: 8
• Operational tool and documentation (Workstream B) - Weeks 14–17, Est days: 4
• RMA methodology guide (Workstream C) - Weeks 15–18, Est days: 4

Ethical Considerations and Data Protection

The IRC takes data protection seriously and operates under its organisation-wide data protection policy. The consultant will be required to sign a data sharing agreement prior to accessing any client-level data. All data provided will be de-identified.

Management and Reporting

The consultant will report to [Philip Blue / Regional Measurement Adviser, Latin America] and work in close coordination with the IRC's Measurement Unit and relevant country programme MEAL staff.

Submission Requirements

• CV highlighting relevant data science experience.
• A short expression of interest (maximum one page) describing your approach to one of the two workstreams.
• Two examples of prior analytical work.
• Daily rate in USD.
• Names and contact details of two referees from previous clients or employers.