Lead AI Platform Engineer

**Salary Range** - £78,000 - £83,000 The Lead AI Platform Engineer role is a foundational engineering enablement role responsible for defining the standards, platform patterns and operating approach required to integrate AI agents within the Inflo platform in a safe, secure and consistent way. This role will establish the guardrails, reference approaches and foundational tooling that enable engineering teams to build, deploy and operate agent capabilities safely. A key part of the role is creating practical guidance for how agents are evaluated, tested, versioned, deployed and monitored in production, with strong observability and operational control. **Responsibilities** As an Audit Methodology Manager at Inflo, you will: - Defining the standards, engineering patterns and target operating model for AI agents within the Inflo platform, including how agent capabilities should be introduced, governed and supported safely - Designing the foundational tooling, pipelines and reference approaches that support the agent lifecycle, including evaluation, testing, versioning, deployment and rollback - Working closely with platform and software engineers to implement shared capabilities, delivery practices and operational patterns that feature teams can adopt consistently - Establishing safe-by-design controls for agent behaviour, including guardrails, governance, monitoring, auditability and human oversight where appropriate - Defining observability standards for agents, including telemetry, quality signals, operational health, incident investigation and continuous improvement loops - Enabling engineering teams to deploy and operate agents in a safe, consistent and supportable way through reusable patterns, reference implementations, documentation and technical coaching - Researching emerging agentic AI technologies, frameworks and practices, and assessing their suitability for use within Inflo’s SaaS platform **Required/desired skills & qualifications** - Strong understanding of AI concepts relevant to agentic systems, including large language models, retrieval patterns, evaluation approaches, prompt and instruction design, and orchestration concepts - Proven experience integrating AI agents or agent-like capabilities into customer-facing SaaS products - Experience defining standards and foundational tooling for the safe lifecycle management of AI systems, including evaluation, testing, versioning, deployment, monitoring and rollback - Experience establishing observability for AI systems, including telemetry, quality measurement, operational monitoring, debugging and incident response - Experience working with software and platform engineers to implement practical engineering standards, shared capabilities and operational practices - Experience creating reusable guidance, reference implementations or enablement approaches that help engineering teams adopt new capabilities consistently - Experience with Microsoft Azure, including AI Foundry, and familiarity with cloud-based AI deployment patterns - Experience with Azure DevOps pipelines and Infrastructure-as-Code, ideally using Bicep - Familiarity with AI ethics, bias mitigation, risk management, data privacy (e.g., GDPR), and emerging regulations such as the EU AI Act - Excellent communication skills, with the ability to collaborate credibly across engineering teams and document technical standards, patterns and guidance clearly **Core values in action** - **Science** – Bringing an evidence-led mindset to the role by using structured evaluation, testing, telemetry and measurable outcomes to shape how agents are designed, introduced and improved across the platform. - **Ownership** – Taking responsibility for establishing the standards, guardrails and foundational tooling that enable safe adoption of AI agents, while working proactively with Platform engineers and product teams to ensure those approaches are implemented effectively. - **Openness** – Collaborating transparently with tec…