Part-time Policy Lens Consultant

Job Posting Organization:
The United Nations Economic and Social Commission for Western Asia (ESCWA) is a regional arm of the United Nations established to promote economic and social development in the Arab region. ESCWA was founded in 1973 and has since been working to foster cooperation among member states, providing a platform for dialogue and collaboration on various socio-economic issues. The organization operates in 17 member states and employs a diverse team of professionals dedicated to addressing the challenges faced by the region. ESCWA's mission includes enhancing the capacity of member states to achieve sustainable development goals, improving regional integration, and promoting social justice and equality.

Job Overview:
The position of Part-time Policy Lens Consultant is designed for a professional who will contribute to the development of a structured evidence-synthesis approach for policy documents. The consultant will be responsible for designing and piloting a small set of policy lenses that will extract structured, comparable representations from policy documents. This role is crucial as it aims to enhance the understanding of how different countries approach specific policy issues by analyzing national strategies, evaluations, and progress reviews. The consultant will work on a feasibility pilot, focusing on one policy domain across three to five ESCWA member states. The outputs generated will be used to evaluate and extend the policy lens framework, providing valuable insights for policymakers. The consultant will also be expected to apply political neutrality in the design of the lenses, ensuring that the findings are framed as opportunities for regional learning rather than as scorecards for individual countries.

Duties and Responsibilities:
The consultant will undertake a variety of duties under the supervision of the Chief of the Decision Support and Data Science Division (DSDS). Key responsibilities include:

• Designing the lens framework by articulating the lens/frame concept and developing a taxonomy of lenses, including descriptive, causal, and gap-detection lenses.
• Ensuring political neutrality in lens design, particularly for gap-detection lenses, by framing findings as opportunities for regional learning.
• Scoping the pilot corpus in collaboration with ESCWA, selecting one policy domain and three to five countries, and identifying well-structured English-language documents for analysis.
• Specifying and testing three to five pilot lenses, ensuring a mix of descriptive, causal, and gap-detection lenses with defined extraction schemas.
• Building a simple extraction and comparison pipeline that includes extraction, structuring into the lens schema, and output generation using LLM APIs.
• Producing structured outputs for policymakers, including tables, comparison views, and visualizations.
• Running an expert validation round to review outputs for substantive accuracy and documenting findings.
• Recommending integration paths for Policy Lens outputs into existing ESCWA systems.
• Documenting and handing over all code, schemas, prompts, and documentation to ensure reproducibility. 1
• Preparing a methods paper based on pilot results for potential submission with ESCWA clearance.

Required Qualifications:
Candidates must possess a Master's degree or equivalent in fields such as computer science, data science, computational linguistics, public policy, economics, or a related area. A PhD is desirable but not mandatory. All applicants are required to submit a copy of their educational degree, as incomplete applications will not be considered. Additionally, candidates must have at least five years of progressively responsible experience in applied natural language processing (NLP), LLM-based systems, or data science. Demonstrated experience in building LLM pipelines for information extraction or structured output is essential, along with proficiency in Python and common LLM/NLP tools. Experience analyzing public policy documents and familiarity with the SDG framework and development indicators are also desirable qualifications.

Educational Background:
The educational background required for this position includes a Master's degree or equivalent in relevant fields such as computer science, data science, computational linguistics, public policy, or economics. A PhD is considered an asset, indicating a higher level of expertise and research capability in the relevant areas. Candidates must provide proof of their educational qualifications as part of the application process.

Experience:
The position requires candidates to have a minimum of five years of progressively responsible experience in applied natural language processing (NLP), LLM-based systems, or data science. This experience should include demonstrated work in building LLM pipelines for information extraction or structured output, which involves schema-constrained generation and prompt design. Candidates should also have experience analyzing public policy documents and familiarity with evidence synthesis, Theory of Change, and results frameworks. Prior work with the UN system or other international organizations, particularly in the Arab region, is highly desirable.

Languages:
Fluency in English is required for this position, as it is one of the working languages of the United Nations Secretariat. Fluency is defined as a rating of 'fluent' in all four areas: speaking, reading, writing, and understanding. Knowledge of French is also beneficial, as it is another working language of the UN. Additionally, Arabic is a working language of ESCWA, and knowledge of Arabic would be advantageous but is not mandatory for this role.

Additional Notes:
The position is part-time and expected to last for a duration of six months. The work location is remote, allowing for flexibility in work arrangements. It is important to note that the United Nations does not charge any fees at any stage of the recruitment process, including application, interview, or training. The organization is committed to ensuring a transparent and fair recruitment process, and it does not require any financial information from applicants.