AI Engineer – Multi‑Agent Systems

About the role

A private investment office in Abu Dhabi is expanding its elite technical team to build and own state‑of‑the‑art multi‑agent orchestration and agentic infrastructure. You will architect the core systems that enable autonomous AI agents to plan, execute tool calls, retry on failure, and reliably hand off complex workflows in production.

Key responsibilities

• Design and build scalable systems for task decomposition, inter‑agent communication, and state management.
• Own sandboxing, guardrails, automated retries, fallback logic, and real‑time observability.
• Build rigorous evaluation pipelines to catch performance regressions before production deployment.
• Architect reliable retrieval (RAG) and tool‑use infrastructure across structured and unstructured data sources.

Required profile

• Deep expertise building with advanced LLM architectures, RAG, agentic reasoning, and multi‑agent workflows.
• A clear grasp of where standard agent frameworks (e.g., ReAct loops) break down and how to engineer resilient workarounds.
• Background in financial services, investment management, fintech, or high‑throughput engineering environments (advantageous).
• Active open‑source contributions, AI research publications, or relevant patents are highly valued.

Required skills

• LangGraph, AutoGen, or custom agent frameworks.
• Model Context Protocol (MCP), vector databases (Pinecone, Qdrant, Chroma, etc.), hybrid search.
• Python (PyTorch/TensorFlow, AsyncIO, FastAPI).

What we offer

• Highly competitive, tax‑free base salary.
• Discretionary performance‑based annual bonus.
• Full visa sponsorship and premium relocation package.
• Comprehensive private health insurance and dependent schooling allowances.