Mid-Level Artificial Intelligence Engineer

About the role

The Consultant will design, develop, and deploy production‑grade agentic AI systems and LLM‑powered solutions for the Arab Development Portal and broader DSDSD innovation initiatives. Working remotely, the role supports ESCWA's modernization agenda by turning cutting‑edge AI research into practical organizational capabilities.

Key responsibilities

• Architect multi‑agent systems using frameworks such as LangGraph, AutoGen or CrewAI, including retrieval‑augmented generation (RAG) pipelines and tool‑use capabilities.
• Integrate, benchmark and fine‑tune state‑of‑the‑art LLMs for Arabic and multilingual tasks, applying prompt engineering and chain‑of‑thought techniques.
• Design RESTful and streaming APIs, containerize services with Docker, and manage deployments in line with ESCWA infrastructure standards.
• Develop evaluation frameworks, conduct automated benchmarking, and iterate on agent performance.
• Collaborate with data engineers, ML engineers and domain experts, and produce technical reports and presentations for diverse stakeholders.

Required profile

• Bachelor’s degree in Computer Science, AI, Data Science or related field (master’s preferred).
• Minimum 5 years of professional experience in AI/ML or software engineering with a focus on AI.
• Hands‑on experience building agentic systems with multi‑agent frameworks.
• Fluency in English (working language of the UN Secretariat).

Required skills

• Python programming.
• Experience with LLM APIs (OpenAI, Anthropic, Mistral, Ollama, HuggingFace).
• Knowledge of RAG architectures and vector databases (FAISS, Weaviate, Qdrant).
• Familiarity with model fine‑tuning methods (LoRA, QLoRA, full fine‑tuning) and evaluation techniques.
• Docker containerization and API development (RESTful/streaming).