Responsibilities
* Design, develop, and maintain Copilot agents, plugins, connectors, and LLM workflows in Copilot Studio
* Build scalable components: prompt orchestration, retrieval layers, Power Automate flows, model interfaces, validation pipelines
* Develop and optimise RAG components — embeddings, vector queries, metadata strategies for accuracy and reliability
* Integrate AI agents with enterprise systems via Microsoft Graph, APIs, and Power Platform connectors
* Implement secure-by-design and responsible AI practices: guardrails, controls, monitoring, auditability
* Build observability: logging, telemetry, and LLM monitoring for quality and incident triage
* Create reusable assets — prompt libraries, agent templates, connectors, test harnesses, and documentation
* Conduct rapid prototyping to validate feasibility, model behaviour, UX, and performance
* Enable pro-/low-/no-code teams to adopt AI safely — support the satellite model across business functions
Requirements
MUST-HAVES
* Hands‑on experience building solutions with LLMs, AI APIs, Copilot Studio, or agent frameworks
* Strong understanding of RAG architectures, vector databases, embeddings, and retrieval optimisation
* Experience with Microsoft Azure AI services, cloud‑native engineering, and secure deployment patterns
* Experience with agent engineering: orchestration, lifecycle management, versioning, drift detection
* Secure‑by‑design mindset — authentication, authorisation, data protection, auditability
* Familiarity with DevOps, CI/CD, IaC, observability, and modern engineering pipelines
* Ability to debug unexpected AI behaviour — hallucinations, variability, reliability issues
* Strong documentation skills and ability to produce reusable code assets and templates
#J-18808-Ljbffr