AI Engineer

Job Summary

Full-stack Software Engineer to build and integrate AI/GenAI-enabled applications, APIs, services, and user interfaces into the bank's enterprise systems. This role delivers reliable, maintainable, production-grade software that consumes large language models (LLMs) and machine-learning models, implements banking-grade guardrails, and integrates with core banking, channels, and workflows — and designs and builds the front-end experiences that staff and customers actually use. Sitting within the AI Centre of Excellence — which fully owns the stabilization period after go-live — the ideal candidate combines strong full-stack engineering craft, a security-first mindset, and the operational discipline to support what the team builds all the way through to a clean hand-over.

Job description

• Develops AI application services, APIs, and integration layers that consume LLMs, ML models, and retrieval services
• Designs and implements the front-end of AI applications — responsive, accessible user interfaces and conversational/chat experiences — from UX wireframes through production code
• Implements GenAI application patterns including retrieval-augmented generation (RAG), agents, tool/function calling, prompt templates, and streaming responses (including streaming UI)
• Applies production-grade engineering practices end-to-end (front-end and back-end): code quality, unit and integration testing, CI/CD, secure coding, and secret management
• Integrates AI applications with banking data and platform components — APIs, event streams, message queues, batch pipelines, and SSO/IAM
• Implements guardrails and safety across the application layer, including PII redaction, content filters, output validation, fallback behaviors, and safe rendering of model output in the UI
• Builds observability into every service and interface: structured logging, metrics, tracing, prompt/response logging, token and latency telemetry, and front-end performance monitoring
• Contributes to runbooks, support playbooks, and the on-call rotation during the stabilization period
• Collaborates with Data Scientists and ML Engineers to operationalize models, prompts, and evaluation hooks, and supports incident troubleshooting and continuous improvement after go-live
• Plans and delivers AI application modules and front-end components with increasing independence, assessing technical feasibility for new GenAI features and supporting integrations
• Introduces engineering best practices and new GenAI techniques to the team, and shares knowledge through code reviews, tech talks, and internal communities

.

Qualifications

• Bachelor's degree in Computer Science, Software Engineering, Information Technology, or a related field (or equivalent practical experience
• At least 3 years of software engineering experience building and operating production web applications, services, and API
• Strong proficiency in Node.js / TypeScript as the primary stack, with Python as a secondary language
• Front-end design and implementation experience: a modern framework (React, Angular, or Vue), HTML/CSS, responsive and accessible UI, and component-based architecture.
• Hands-on experience with REST APIs, Git, CI/CD pipelines (Azure DevOps or GitHub Actions), containerization (Docker), and automated testing (front-end and back-end).
• Familiarity with LLM application concepts: prompt design, RAG, embeddings/vector search, function/tool calling, and building streaming/chat UI
• Understanding of secure coding practices, safe handling of sensitive data (PII), and front-end security (XSS, safe rendering of model output)
• Exposure to at least one major cloud platform — Microsoft Azure preferred (Azure OpenAI, Azure AI Search, AKS a strong plus)
• Experience in banking, financial services, or other regulated environments is an advantage
• Comfortable working in an Agile / Scrum environment