Midlevel Artificial Intelligence Engineer

Job Posting Organization:
The job posting organization is the United Nations Economic and Social Commission for Western Asia (ESCWA), which was established in 197

• ESCWA aims to promote economic and social development in the Arab region through regional cooperation and integration. The organization focuses on various areas including sustainable development, social justice, and economic growth. ESCWA operates in multiple countries across the Arab region, providing support to member states in their development efforts. The organization employs a diverse workforce of professionals dedicated to addressing the unique challenges faced by the region.

Job Overview:
The position of Midlevel Artificial Intelligence Engineer is critical for the Decision-Support and Data Science Division (DSDSD) of ESCWA. The primary objective of this role is to design, develop, and deploy production-grade agentic AI systems and large language model (LLM)-powered solutions that support the Arab Development Portal and the broader innovation mandate of DSDSD. The engineer will be at the forefront of the rapidly evolving AI landscape, translating the latest research advances into practical organizational capabilities. This role requires a deep understanding of AI technologies and the ability to implement them effectively to enhance decision-making processes within ESCWA and its member states. The engineer will work closely with data engineers, machine learning engineers, and domain experts to integrate AI capabilities into end-to-end data products, ensuring that the solutions developed are aligned with the strategic goals of the organization.

Duties and Responsibilities:
The Individual Contractor will be responsible for a variety of tasks, including:

• Designing and developing agentic AI systems by architecting and implementing multi-agent systems using frameworks such as LangGraph, AutoGen, CrewAI, or equivalent. This includes creating systems capable of orchestrating complex reasoning, retrieval, and action pipelines.
• Deploying Retrieval-Augmented Generation (RAG) systems with advanced retrieval strategies for knowledge-intensive tasks.
• Implementing tool-use, multi-agent communication protocols, and function-calling patterns that enable agents to interact with external APIs, databases, and computational tools.
• Developing agent evaluation frameworks that include automated benchmarking, failure analysis, and iterative improvement loops.
• Integrating and optimizing state-of-the-art LLMs across various use cases, applying techniques such as prompt engineering and structured output generation.
• Designing and implementing RESTful and streaming APIs to expose AI capabilities to internal systems.
• Containerizing AI services using Docker and managing deployments according to organizational standards.
• Continuously monitoring and evaluating emerging AI research to identify opportunities for adoption.
• Preparing technical reports and presentations to communicate findings to both technical and non-technical stakeholders.

Required Qualifications:
Candidates must possess a bachelor's degree in computer science, artificial intelligence, data science, or a related field. A master's degree in a related area is desirable. Additionally, candidates must have a minimum of 5 years of professional experience in AI/ML engineering or software engineering with a demonstrated focus on AI. Hands-on experience in designing and deploying agentic systems using multi-agent frameworks is required, along with proficiency in Python and experience with LLM APIs. Knowledge of the current LLM and AI landscape, including model capabilities and limitations, is essential. Familiarity with RAG architectures and vector databases is desirable, as is knowledge of Arabic NLP and multilingual model handling.

Educational Background:
The educational background required for this position includes a bachelor's degree in computer science, artificial intelligence, data science, or a related area. A master's degree in a related field is considered an asset. All candidates must submit a copy of their educational degree, as incomplete applications will not be reviewed.

Experience:
The position requires a minimum of 5 years of professional experience in AI/ML engineering or software engineering, with a strong emphasis on AI. Candidates should have hands-on experience in designing and deploying agentic systems using multi-agent frameworks, as well as proficiency in Python and experience with LLM APIs.

Languages:
Fluency in English is required for this position, which 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 one of the working languages of the United Nations Secretariat. Additionally, knowledge of Arabic is desirable, as it is a working language of ESCWA.

Additional Notes:
This recruitment is conducted on a local basis, meaning that the incumbent must have the legal right to live and work in Lebanon. The position is for a duration of 3 months, and 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.