AI Automation Engineer - Payments

The bank is building a next-generation AI Payments Engineering capability to design and deliver an AI-native Payments Operating System. The AI Automation Engineer will combine AI engineering, systems integration and production automation to transform high-effort, high-risk Payments processes into scalable, intelligent and auditable workflows. The objective is efficiency with control integrity, not automation speed alone.

Core Focus

Design, build, test, deploy and maintain production-grade AI automation workflows that deliver measurable operational impact across Payments.

Illustrative Use Cases

• Payments reconciliations and exception handling.
• Audit and reporting preparation.
• Financial analytics and operational insight.
• Incident detection, triage and response automation.
• Least-cost routing and related Payments decision processes.
• Agentic workflow engineering: Design and deploy multi-step AI workflows using LLM orchestration, tools, agents and workflow engines.
• Software engineering: Build orchestration services using Java with Spring AI and/or Python-based frameworks.
• Model integration: Integrate Claude or Anthropic APIs and comparable enterprise AI services.
• Workflow orchestration: Use n8n or equivalent engines to coordinate reliable, supportable automation.
• Agent and tool integration: Use MCP or comparable context, tool and agent-coordination approaches where appropriate.
• Systems integration: Connect internal and external services through APIs, data pipelines and reporting systems.
• Automation discovery: Identify high-value opportunities to reduce manual effort across Payments operations.
• Production ownership: Test, deploy, monitor, maintain and optimise solutions and supporting platform components.
• Human oversight: Design human approvals and intervention points for high-risk or judgement-dependent activities.
• Classify proposed automation by risk tier before development.
• Ensure every solution has a named Process Owner and documented data flows.
• Implement appropriate access controls, audit logging and traceability.
• Understand and mitigate LLM and agent failure modes in high-stakes environments.
• Preserve control integrity, compliance and auditability throughout the automation lifecycle.
• Develop reusable frameworks, templates, components and workflow patterns.
• Create engineering documentation and standards that support adoption at scale.
• Build dashboards and metrics covering efficiency gains, cost reduction, risk outcomes and return on investment.
• Train Payments teams on AI-enabled workflows and tools.
• Hands-on experience deploying production-grade AI, GenAI or agentic systems.

.special-hidden { display: none; }