Agentic AI Engineer

Agentic AI Engineer 💰 £100,000 to £120,000 📍 London based, two office days per week, with monthly travel to the UAE. Option to relocate to UAE! Company \& role This role sits with a global IT solutions provider building a new AI delivery capability for banking, insurance and fintech clients. AI is already central to what they do. This team build is about scaling that into production grade solutions their financial services customers can rely on. This is a mission critical hire. You will design, build and operate production agentic AI systems that reason, use tools, hold state, retrieve knowledge, run multi step workflows and escalate safely to a human when they should. The focus is turning LLM concepts into reliable, observable services with proper failure handling and guardrails, not demos that fall over in front of a regulator. You will work across model selection, orchestration, tool use, retrieval, evaluation, safety and cost, owning agent behaviour end to end in an environment where correctness and auditability actually matter. Why This Role Stands Out This is production agentic AI for real, in a setting where reliability, safety and cost have genuine consequences. You are not building throwaway prototypes, you are shipping agents that stand up in regulated financial services. You get real depth and ownership across the whole agent lifecycle, from architecture and prompting through tool integration, retrieval, evaluation and observability, backed by a modern stack and GPU inference. It is early enough that you help set the patterns for how agents are built and governed here, you move at pace without heavy process, and there is strong international exposure through regular time in the UAE. Key Responsibilities * Design, build and operate production agentic AI systems that reason, use tools, maintain state, retrieve knowledge and escalate safely to humans * Select and integrate LLMs and agent frameworks across Azure OpenAI, Anthropic and open models, balancing latency, cost, quality, data residency and compliance * Engineer reliable tool use, including function calling, structured outputs, MCP servers, API wrappers, permissions, retries, timeouts, sandboxing and audit trails * Implement retrieval, memory and context patterns including RAG, hybrid search, re ranking, short and long term memory, summarisation and context budgeting * Own agent evaluation, safety and observability, including automated evals, golden datasets, red team testing, prompt injection defences, PII controls, tracing and dashboards * Design agent architecture, decision loops and multi turn conversation handling, with error recovery and clear escalation paths * Optimise performance and commercial viability through token budgeting, prompt caching, model routing, batching and cost monitoring * Deploy agents as reliable services using CI and CD, environment separation, secrets management, feature flags, canary releases, rollback and provider failover * Work closely with backend, quality and data colleagues to define agent friendly API contracts and robust test scenarios Ideal Experience Essential * 4 or more years in software, machine learning or production AI engineering, with evidence of shipping reliable services beyond prototypes * 2 or more years working with LLMs, across prompt and context engineering, structured outputs, function calling, RAG, evaluation and production monitoring * Experience with agent frameworks such as LangGraph, LangChain, LlamaIndex, Semantic Kernel, AutoGen, CrewAI or the OpenAI Agents SDK, or comparable custom orchestration * Strong Python engineering, including async programming, type hints, validation, API design, test automation and secure, maintainable service architecture * Deep understanding of agentic patterns such as ReAct, plan and execute, reflection, state graphs, multi agent orchestration, memory design and human in the loop controls * Solid grasp of retrieval and context systems, including embeddings, vector databases, hybrid search, re ranking, access controlled RAG and provenance * Security and governance knowledge covering prompt injection, data exfiltration, PII handling, sandboxing, approvals and audit evidence * Financial services, banking, insurance or fintech domain experience (mandatory) Desirable * MCP server authoring and agent to agent communication protocols * Agent evaluation tooling such as LangSmith or Braintrust, and observability with Application Insights * Multimodal agents, and Arabic or UAE localisation * Regulated industry AI governance experience * On premise or local inference with vLLM or TensorRT LLM, and model routing for cost and performance