AI Architect, Enterprise Agentic AI Architecture

Job Purpose

Key Accountabilities

• Own enterprise Agentic AI architecture, reference patterns, reusable components, and governance guardrails.
• Architect conversational AI and agent platforms for retail banking journeys.
• Translate business, product, and regulatory requirements into secure, resilient, and observable architectures.
• Design multi-agent ecosystems with orchestration, tools, memory, context management, evaluation, and human-in-the-loop controls.
• Lead RAG architecture including retrieval, semantic indexing, vector databases, grounding, and answer quality.
• Define standards for evaluation, guardrails, auditability, observability, safety, performance, and business outcomes.
• Architect secure integration with APIs, backend systems, middleware, channels, data platforms, AI services, and third-party tools.
• Create ADRs, solution architecture documents, integration designs, and ARB presentations.

Delivery Scope

• Guide implementation of production-grade banking agents with tool execution, transaction flows, and contextual customer support.
• Design agentic workflows for payments, transfers, account and card servicing, and self-service fulfilment.
• Design human-in-the-loop approval, exception handling, escalation, operational review, and sensitive-journey controls.
• Define memory, privacy, context engineering, evaluation, tool integration, and interoperability patterns.
• Design security controls including zero trust, least privilege, PII redaction, data masking, filtering, secure logging, and audit mechanisms.
• Design deployment architecture using Azure AI, Azure OpenAI, AWS AI services, Amazon Bedrock, Kubernetes, serverless components, and observability tools.
• Provide hands-on technical direction and mentor AI engineers and architects.

Qualifications and Experience

• Bachelor’s or Master’s degree in Computer Science, Software Engineering, Information Technology, Artificial Intelligence, Data Science, or a related discipline.
• Senior technology professional with around 12 or more years across software engineering, architecture, cloud or platform engineering, and enterprise solution delivery.
• At least 4 years of hands-on AI engineering or AI architecture experience with Generative AI, LLM applications, and Agentic AI solutions.
• Proven experience architecting and delivering multiple production-grade banking agents or banking chat assistants.
• Strong understanding of retail banking, payments, transfers, servicing, self-service, operational controls, and regulatory or security considerations.
• Full AI engineering capability including Python, APIs, microservices, event-driven design, RAG, evaluation, and cloud-native deployment.
• Experience with agent frameworks, orchestration platforms, MCP servers, tool integration, A2A, A2UI, and related protocols.
• Experience with Azure AI, Azure OpenAI Service, AWS AI services, Amazon Bedrock, and model deployment capabilities.
• Experience designing secure AI systems with zero trust, identity controls, data protection, PII redaction, and privacy-by-design.
• Experience presenting architecture recommendations, trade-offs, ADRs, and solution designs to ARB or equivalent forums.

Key Technical Skills

• Enterprise Agentic AI architecture, multi-agent systems, autonomous workflows, human-in-the-loop design, and banking chat assistants.
• LLMs, prompt engineering, context engineering, memory design, tool calling, orchestration, evaluation, and cost or latency optimization.
• RAG, semantic indexing, embeddings, vector databases, retrieval optimization, reranking, grounding, and explainability.
• MCP server architecture, tool registries, multi-tool integration, A2A, A2UI, and agent interoperability.
• Azure AI, Azure OpenAI, AWS AI services, Amazon Bedrock, Kubernetes, serverless, microservices, APIs, event-driven architecture, and observability.
• AI security architecture including zero trust, PII redaction, data masking, privacy controls, guardrails, secure logging, and auditability.

Leadership Skills

• Strategic architecture thinking and ability to define enterprise standards and influence platform direction.
• Strong stakeholder communication for presenting architecture options, risks, trade-offs, and recommendations.
• Collaborative leadership across business, product, engineering, cybersecurity, data, infrastructure, operations, compliance, and enterprise architecture teams.
• Hands-on problem solving, pragmatic decision making, ownership, mentoring, and responsible AI mindset.

Preferred Qualifications

• Relevant certifications in cloud architecture, AI engineering, security architecture, enterprise architecture, or machine learning are preferred.
• Prior experience building AI agent ecosystems in regulated financial services or large-scale digital banking is advantageous.
• Hands-on experience with Microsoft Semantic Kernel, AutoGen, LangChain, LangGraph, Microsoft Agent Framework, or equivalent capabilities is advantageous.