AI Engineer – Generative AI and Automation

Welcome to **MultiBank Group**, a global financial pioneer established in 2005 in California and now proudly headquartered in Dubai, UAE. We specialize in delivering cutting-edge trading technology, unparalleled liquidity, and exceptional customer service. Our extensive range of financial products includes Forex, Metals, Shares, Indices, Commodities, and Cryptocurrency CFDs. Join our thriving community of over 2 million clients across 100 countries, contributing to a daily trading volume exceeding US$ 35 billion. As a heavily regulated institution with oversight from 18+ financial regulators across 5 continents, and recipient of over 80 financial awards, MultiBank Group is devoted to innovation, excellence, and empowering our clients to achieve their financial goals. **Role Overview** We are seeking an AI Engineer to design, build, and deploy intelligent AI agents and automated workflows that address real business problems. This is a hands-on, high-impact role within the Artificial Intelligence and Advanced Analytics team. The successful candidate will own end-to-end delivery of AI agents from scoping and architecture through integration, testing, and production deployment, enabling the organization to automate complex processes and unlock value from generative AI. **Key Responsibilities** * Design, build, and deploy AI agents using frontier LLMs including Claude (Anthropic API), OpenAI, Gemini, and other frontier models * Architect multi-agent systems and agentic workflows using frameworks including LangChain, LangGraph, CrewAI, AutoGen, and Semantic Kernel * Build and manage automated business workflows using n8n, Make (Integromat), Zapier, and custom API integrations * Implement RAG pipelines with vector databases including Pinecone, Weaviate, Qdrant, and pgvector to give agents access to organizational knowledge bases * Design tool-use and function-calling integrations, connecting agents to internal systems, APIs, databases, and third-party services * Fine-tune and prompt-engineer LLMs to optimize agent behavior, reliability, and task accuracy * Collaborate with business stakeholders to identify automation opportunities and translate requirements into agent-based solutions * Monitor, evaluate, and continuously improve deployed agents across quality, latency, cost, and safety metrics * Establish and maintain best practices for agent safety, guardrails, human-in-the-loop controls, and responsible AI deployment * Develop MCP (Model Context Protocol) server integrations to extend agent capabilities **Requirements** * Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Software Engineering, or a related field; equivalent practical experience will be considered * 2 or more years of hands-on experience building production AI systems or intelligent automation solutions * Demonstrated experience building agents or workflows with LangChain, LangGraph, CrewAI, n8n, or comparable frameworks * Proven ability to integrate LLM APIs including Anthropic Claude and OpenAI into real-world applications * Experience with vector databases and semantic search implementations is strongly preferred * Portfolio or demonstrable projects showing deployed agents, automation workflows, or RAG-based applications * Proficiency in Python as the primary language; JavaScript or TypeScript is beneficial * Familiarity with cloud platforms, Docker, FastAPI, and CI/CD practices for AI pipelines **Technical Skills** **LLM APIs**: Anthropic Claude (claude-opus-4, claude-sonnet-4), OpenAI GPT-4o, Google Gemini, Mistral **Agent Frameworks**: LangChain, LangGraph, CrewAI, AutoGen, Semantic Kernel, Haystack **Workflow Automation:** n8n, Make (Integromat), Zapier, Apache Airflow **Vector Databases and RAG:** Pinecone, Weaviate, Qdrant, pgvector, Chroma, LlamaIndex **Programming:** Python (primary), JavaScript/TypeScript, REST API design **Cloud and MLOps:** AWS, Azure, GCP, Docker, FastAPI, CI/CD for AI pipelines **Observability and Evaluation:** LangSmith, Helicone, Weights and Biases, custom evaluation harnesses **AI Agent Focus Areas** * Autonomous and semi-autonomous agents for customer service, operations, marketing, and data analysis * Multi-agent orchestration including planner, executor, critic, and memory agent patterns * Knowledge retrieval systems including enterprise RAG, document Q&A, and semantic search * Process automation integrating CRM, ERP, and communication tools end-to-end * Agent safety, guardrails, and human-in-the-loop oversight mechanisms * MCP server development for extending agent capabilities **Soft Skills** * Strong problem-solving ability and analytical thinking * Ability to translate complex business needs into practical technical solutions * Effective collaboration and communication in a team-oriented environment * Intellectual curiosity and commitment to staying current with AI research and trends **Why Join Us?** * *Work with one of the world’s leading financial derivati