Part-Time Policy Lens Consultant
Overview
The consultant will design and pilot a structured evidence-synthesis approach for policy documents, demonstrating its value on a bounded corpus from a small number of ESCWA member States.
Key Responsibilities
- Design the lens framework, articulating the concept and developing a taxonomy of lenses.
- Build neutrality into lens design, especially gap-detection lenses.
- Scope the pilot corpus with ESCWA, agreeing on a policy domain and countries.
- Specify and test three to five pilot lenses, including descriptive, causal, and gap-detection lenses.
- Build a simple extraction and comparison pipeline using LLM APIs.
- Produce structured outputs for policymakers, such as tables, comparison views, and visualizations.
- Run an expert validation round to review outputs for substantive accuracy.
- Recommend integration paths for Policy Lens outputs into existing systems.
- Document and hand over code, schemas, prompts, and documentation.
- Prepare a methods paper on the lens/frame approach.
Required Experience
At least five years of progressively responsible experience in applied NLP, LLM-based systems or data science is required. Demonstrated experience building LLM pipelines for information extraction or structured output (schema-constrained generation, prompt design, evaluation) is required. Experience analyzing public policy documents, evidence synthesis, or Theory of Change and results frameworks is desirable. Familiarity with the SDG framework and development indicators is desirable. Experience with retrieval-augmented or multi-agent systems is desirable. Publications in NLP, computational social science or policy analytics is desirable. Prior work with the UN system or other international organizations, particularly in the Arab region is desirable.
Qualifications
A Master's degree or equivalent in computer science, data science, computational linguistics, public policy, economics or related area is required. A PhD is desirable. Proficiency in Python and common LLM/NLP tooling is required.