Mid-Level Artificial Intelligence Engineer

United Nations - UN •Economic and Social Commission for Western Asia

Consultant Closes 05 Oct 2026 5 days left

Overview

Design, develop, and deploy agentic AI systems and LLM-powered solutions to support the Arab Development Portal and broader innovation mandates.


Key Responsibilities
  • Architect and implement multi-agent systems using frameworks such as LangGraph, AutoGen, CrewAI, or equivalent.
  • Design and deploy Retrieval-Augmented Generation (RAG) systems.
  • Implement tool-use, MCPs, and function-calling patterns.
  • Develop agent evaluation frameworks.
  • Integrate and benchmark state-of-the-art LLMs.
  • Apply prompt engineering, structured output generation, and chain-of-thought techniques.
  • Explore and implement fine-tuning strategies.
  • Monitor and optimize inference costs, latency, and throughput.
  • Design and implement RESTful and streaming APIs.
  • Containerize AI services using Docker.
  • Maintain documentation, versioning, and model cards.
  • Continuously monitor and evaluate emerging AI research, frameworks, and tooling.
  • Collaborate with data engineers, ML engineers, and domain experts.
  • Prepare technical reports, demonstrations, and presentations.
Required Experience

A minimum of 5 years of professional experience in AI/ML engineering or software engineering with a demonstrated AI focus is required. Hands-on experience designing and deploying agentic systems using multi-agent frameworks (LangGraph, AutoGen, CrewAI, or equivalent) is required. Proficiency in Python and experience with LLM APIs (OpenAI, Anthropic, Mistral, or open-source alternatives via Ollama or HuggingFace) is required. Demonstrated knowledge of the current LLM and AI landscape, including frontier model capabilities, benchmarks, and limitations, is required. Experience with RAG architectures, vector databases (FAISS, Weaviate, Qdrant, or equivalent), and semantic search is desirable. Familiarity with model fine-tuning, RLHF, and evaluation methodologies is desirable. Knowledge of Arabic NLP and multilingual model handling is desirable.

Qualifications

A bachelor's degree in computer science, artificial intelligence, data science or a related area is required. A master's degree in a related field is desirable.

Other Details
Languages Required
Fluency in English is required.
Languages Preferred
Knowledge of Arabic NLP and multilingual model handling is desirable. A master's degree in a related field is desirable. Experience with RAG architectures, vector databases (FAISS, Weaviate, Qdrant, or equivalent), and semantic search is desirable. Familiarity with model fine-tuning, RLHF, and evaluation methodologies is desirable.
Contract Duration
3 months
Work Modality
UN-House ESCWA
Remuneration
Not specified
Apply

Similar Opportunities