Description
This role builds secure, scalable and production-ready AI capabilities that create measurable value for customers and colleagues.
You’ll design, deploy and operate enterprise-grade solutions across generative AI, large language models, agentic AI, Retrieval-Augmented Generation (RAG) and AI platform engineering.
Working in a regulated banking environment, you’ll partner closely with Product, Architecture, Engineering, Data, Cybersecurity and Risk to ensure services are resilient, observable, auditable and appropriately controlled.
Success means moving AI opportunities safely from concept to production with clear non-functional requirements for performance, security, cost and service ownership.
You’ll deliver trusted AI services that meet real needs and can be reused across products rather than creating isolated technology stacks.
Responsibilities
- Design, build, test and operate production-grade AI and generative AI services
- Engineer AI agents and agentic workflows, including tool use, function calling, orchestration and human-in-the-loop controls
- Build RAG solutions using enterprise knowledge, search, embeddings, vector retrieval and approved data sources
- Develop context and memory capabilities to support effective knowledge retrieval and appropriate session continuity
- Create robust Python services, APIs and integration components connecting AI capabilities with applications, platforms and workflows
- Productionise proofs of concept with clear requirements for performance, resilience, security, cost and service ownership
- Implement CI/CD and MLOps/LLMOps practices, including automated testing, version management, controlled deployment and rollback
- Define evaluation approaches covering quality, safety, grounding, latency, cost and responsible AI
Requirements
- Bring strong hands-on Python software engineering experience, including backend services and APIs
- Demonstrate practical experience designing, delivering and operating enterprise AI, ML or generative AI applications in production
- Apply strong understanding of LLM application patterns, prompting, structured generation, function calling and model evaluation
- Use hands-on experience with RAG, embeddings, enterprise search and vector retrieval
- Build AI agents or orchestrated AI workflows, including failure handling and appropriate human oversight
- Work with at least one major cloud AI platform such as Google Cloud Vertex AI or Microsoft Azure AI
- Apply strong automated testing, source control, CI/CD and modern software engineering practices
- Use knowledge of AI security, privacy, governance, auditability and operational controls
- Translate business and user needs into practical technical designs and production outcomes
- Communicate clearly with technical and non-technical stakeholders and support the development of other engineers
For more fresh new jobs, check out yubhub.co.