Artificial Intelligence Engineer/Researcher - ABM/LLM Integration

Organizational Context

The United Nations Economic and Social Commission for Western Asia (ESCWA), specifically its Decision-Support and Data Science Division (DSDS), is seeking an AI Engineer/Researcher. This role supports ESCWA's mandate to foster sustainable development in the Arab region through evidence-based policymaking and digital innovation. The position will develop advanced AI tools, including integrating Large Language Models (LLMs) with Agent-Based Modelling (ABM).

Job Purpose

The purpose of this consultancy is to research, develop, and validate an integrated Agent-Based Modelling (ABM) and Large Language Model (LLM) framework. This framework will enhance AI-driven policy analysis for the Arab region, contributing to ESCWA's AI for Policy program. The role involves creating deployable decision-support prototypes and publications for member states. Key objectives include delivering a validated ABM model, conducting a literature review on ABM+LLM integration, designing and implementing an ABM+LLM architecture where LLMs act as tools and autonomous agents, and benchmarking the integrated model against alternative LLM-based decision-support approaches. The initiative aims to leverage LLMs for natural language reasoning, contextual intelligence, and adaptive policy advisory capabilities within complex socioeconomic simulations.

Responsibilities

The consultant will be responsible for improving the calibration and robustness of an existing rule-based ABM model, conducting scalability tests, and defining validation metrics. This includes simulating policy scenarios, analyzing results, and producing policy-relevant insights. A comprehensive literature review on ABM+LLM integration will be conducted, followed by the design of a conceptual architecture specifying LLM roles. The consultant will develop and deploy the first version of the LLM-enhanced ABM model, integrating LLMs as analytical tools. Rigorous benchmarking against established LLM-based decision-support approaches will be performed. LLMs will be integrated as autonomous agents, and the model will be shared for participatory validation and refinement. Finally, the consultant will deploy the LLM-empowered ABM model to the DSDS GitHub repository.

Work Experience

A minimum of two years of demonstrated experience in agent-based modelling, complex systems simulation, or computational social science is required. Proven experience with large language models (prompt engineering, fine-tuning, API integration) is necessary. Experience with Python-based ABM frameworks and LLM integration libraries is also required. Familiarity with policy-relevant simulation use cases is desirable.

Skills

Agent-Based Modelling (ABM), Large Language Models (LLMs), prompt engineering, fine-tuning, API integration, Python-based ABM frameworks, LLM integration libraries, version control (Git/GitHub), reproducible research practices, analytical and research skills, technical report writing, policy analysis.

Explore related opportunities