Mid-Level Artificial Intelligence Engineer
Organizational Context
The Economic and Social Commission for Western Asia (ESCWA), within the UN Secretariat, is modernizing and innovating through its Decision-Support and Data Science Division (DSDSD). DSDSD provides advanced analytics and decision-support services to ESCWA, UN entities, and Member States, aligning with the UN 2.0 agenda. It leverages data, emerging technologies, and strategic foresight to inform policymaking and operations.
Job Purpose
This role aims to keep the organization at the forefront of AI advancements, specifically in large language models, multi-agent frameworks, and AI-assisted workflows. The consultant will translate cutting-edge research into practical organizational capabilities, contributing to the modernization and innovation efforts of ESCWA. The position supports the Arab Development Portal and the broader DSDSD mandate by developing and deploying advanced AI solutions. The work involves designing, developing, and implementing production-grade agentic AI systems and LLM-powered solutions, ensuring they are integrated into end-to-end data products and effectively support evidence-based decision-making, organizational efficiency, and strategic innovation across the region.
Responsibilities
Key responsibilities include architecting and implementing multi-agent systems using frameworks like LangGraph or AutoGen, and designing Retrieval-Augmented Generation (RAG) systems with advanced retrieval strategies. This involves integrating and benchmarking state-of-the-art LLMs for various tasks, applying prompt engineering, and exploring fine-tuning techniques. The role also requires designing and implementing APIs for AI capabilities, containerizing services with Docker, and managing deployments. Continuous research into emerging AI trends and collaboration with data and ML engineers are essential. Additionally, the consultant will prepare technical reports and presentations to communicate AI system designs and findings to diverse stakeholders.
Work Experience
A minimum of 5 years of professional experience in AI/ML engineering or software engineering with a strong AI focus is required. Hands-on experience designing and deploying agentic systems using multi-agent frameworks is essential. Experience with RAG architectures and vector databases is desirable.
Skills
Proficiency in Python; Experience with LLM APIs (OpenAI, Anthropic, Mistral, open-source alternatives); Knowledge of current LLM and AI landscape; Experience with RAG architectures and vector databases; Familiarity with model fine-tuning and evaluation; Knowledge of Arabic NLP and multilingual models; Experience with multi-agent frameworks (LangGraph, AutoGen, CrewAI); API development (RESTful, streaming); Containerization (Docker).