Lead Agentic AI Engineer – Enterprise Data Platform (EDP)

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:As the Lead Agentic AI Engineer within the Enterprise Data Platform (EDP) at MultiBank Group, you will define and build MBG’s agentic AI capability. The EDP provides the governed data foundation for analytics, machine learning, and AI across the Group, and MBG has launched a Group-wide initiative to design and deploy AI agents for Sales, Marketing, Finance, Operations, Customer Service, and Compliance.You will own the end-to-end lifecycle of AI agents, from use-case discovery with business teams through architecture, development, evaluation, deployment, and production monitoring. You will set the technical direction, standards, and reference architecture for agent development at MBG while remaining hands-on, and you will lead and mentor AI engineers. You will work closely with data engineers, platform and security teams, and business leaders, reporting directly to the Head of Data & AI.Key ResponsibilitiesAgentic AI Design & DevelopmentDesign, build, and deploy single- and multi-agent systems that automate workflows and decision support across Sales, Marketing, Finance, Operations, and other business domains.Implement agent patterns including tool use, planning, memory, retrieval-augmented generation (RAG), and multi-agent orchestration.Build integrations to enterprise systems (EDW/Redshift, CRM, Back Office, payments, support, and marketing platforms) using APIs and Model Context Protocol (MCP) servers.Partner with business stakeholders to identify high-value use cases, define success metrics, and convert them into production agents.Evaluation, Reliability & SafetyEstablish evaluation frameworks for agents covering task success, accuracy and groundedness, regression testing, and cost and latency benchmarks.Implement guardrails, human-in-the-loop checkpoints, permission scoping, and fallback behavior for sensitive financial and compliance workflows.Monitor agents in production for quality, drift, hallucination, failure modes, and misuse, and drive continuous improvement.Cloud AI Platform EngineeringBuild and operate agent and LLM workloads on AWS (Bedrock, Bedrock Agents/AgentCore, Lambda, ECS/EKS, Step Functions, SageMaker where appropriate).Evaluate and integrate foundation models (Claude, OpenAI, and open-source) with attention to quality, cost, and data-residency requirements.Collaborate with platform and security teams on scalability, identity and access, secrets management, observability, and cost control (FinOps for LLM usage).LLMOps & Engineering ExcellenceImplement CI/CD, versioning for prompts, tools, and agent configurations, automated testing, and release practices for agent systems.Build reusable components, SDKs, and templates so business-aligned teams can build agents consistently and safely.Ensure production-quality code, documentation, and runbooks.Data CollaborationWork with data engineers to consume curated EDW datasets and to expose governed data and semantic layers (e.g., business glossary, metadata) to agents.Define retrieval and knowledge strategies (vector stores, structured query tools, text-to-SQL with guardrails) aligned with enterprise data models and governance standards.AI Governance, Security & ComplianceEnsure agents comply with MBG’s AI governance policy, data classification rules, and regulatory requirements, keeping PII and sensitive trading data within approved boundaries.Provide auditability, traceability (prompt, tool-call, and decision logs), and explainability for agent actions.Contribute to the AI Governance Committee’s standards and approval processes.Technical LeadershipLead, mentor, and grow AI engineers; run design and code reviews.Define the agentic AI roadmap, reference architectures, and engineering standards with the Head of Data & AI.Communicate trade-offs and results clearly to senior and non-technical stakeholders.Continuously evaluate emerging models, frameworks, and agent tooling.Qualifications & RequirementsExperience & Education8+ years of experience in software engineering, ML, or AI engineering, including 2+ years building LLM/agentic systems with at least one delivered to production.Experience leading or mentoring engineers; technical lead experience preferred.Bachelor’s degree in Computer Science, Engineering, Mathematics, Data Science, or a related field.Master’s degree or relevant certifications (AWS ML Specialty, AWS AI Practitioner/Developer, other AI certifications) are a plus.Agentic AI & LLM EngineeringProven experience building and deploying LLM-based agents in production (tool/function calling, orchestration, RAG, memory, multi-agent workflows).Hands-on with agent frameworks and protocols such as LangGraph, LangChain, LlamaIndex, Strands, or the Claude/OpenAI agent SDKs, and MCP.Strong prompt and context engineering skills, and experience with LLM evaluation (offline evals, LLM-as-judge, human review) and observability tooling.Understanding of guardrails, prompt-injection risks, and safe tool-permission design.AWS & CloudStrong hands-on experience with AWS Bedrock (and Agents/AgentCore), plus Lambda, API Gateway, IAM, and containerized deployments (Docker; ECS/EKS a plus).Experience with SageMaker or other ML platform services is an advantage.Programming & Open SourceExpert Python; experience building APIs and services (FastAPI or similar).Familiarity with open-source ML/NLP libraries (Hugging Face, scikit-learn, etc.) and vector databases/search.Ability to write clean, tested, maintainable production code.Data & PlatformsSolid grounding in data pipelines, warehousing, and SQL; experience with Redshift, Snowflake, or Databricks is a plus.Experience with data governance and metadata tooling (e.g., OpenMetadata) is a plus.Domain ExperienceFinancial services, trading, FX, crypto, or other regulated industry experience preferred.Understanding of data privacy, compliance, and risk considerations for AI systems.Leadership & Behavioral CompetenciesOwnership mindset and the ability to deliver independently in a lean, fast-moving team.Proven ability to lead and mentor engineers and set technical standards.Strong stakeholder management: able to translate business problems into agent designs and explain AI concepts to non-technical leaders.Pragmatic balance of engineering rigor and rapid AI-driven innovation.Why Join Us?Build and lead MBG’s agentic AI capability from the ground up, with a Group-wide mandate across Sales, Marketing, Finance, Ops, and more.Own the full agent lifecycle in production, not just prototypes.Direct access to a governed, AI-ready enterprise data foundation (EDP/EDW) and executive sponsorship.Shape AI standards, architecture, and governance at Group level, reporting to the Head of Data & AI.Work on high-impact, high-volume data in a global financial organization.Work with an industry-leading global financial institution.Competitive salary and comprehensive employee benefits.Opportunities for professional growth and career advancement.Collaborative, inclusive, and dynamic work environment.Become part of our international community at MultiBank Group, dedicated to excellence, innovation, and shaping the future of finance.