Site Reliability Engineer – AI-Assisted Engineering

Site Reliability Engineer Home-based (Remote-first, with occasional travel to our Hemel Hempstead HQ and off-site events) Permanent | Full Time Competitive salary + bonus and benefits About the role Fascinated by how AI is reshaping software engineering, and want to help a modern engineering team get genuinely good at it? If so, we want to hear from you! Haven is hiring a Site Reliability Engineer to lead the way on AI-assisted and agentic engineering across our Product Technology function, and to make sure the platforms underneath are every bit as reliable, observable and safe as the AI tooling running on top. This is an AI-first SRE role. You’ll shape how our engineers plan, design, build and validate software in a world where coding harnesses, agents and context engineering are now core to the craft. You’ll define the standards, the guardrails, the tooling choices and the day-to-day practice, and you’ll coach engineers across the function to work alongside AI confidently and effectively. Alongside that, you’ll bring an SRE lens to our wider estate: CI/CD, observability, incident management, cloud and database reliability. The reliability discipline is the thread that ties it all together, applied as much to our AI workflows as to our runtime systems. Your Opportunity Define and evolve the strategy, standards and tooling for AI-assisted and agentic software engineering across HavenChampion safe, effective adoption of coding harnesses and agentic tools (for example Claude Code, Copilot, Cursor), including selection, configuration, governance and cost controlBuild and curate our context engineering practice, including project and system context, prompt libraries, retrieval and memory setups that help engineers get consistently good resultsDesign agentic workflows, evals and feedback loops that give engineers confidence in AI-generated output, and tighten the loop over timeEstablish observability, guardrails and policies around LLM usage, so we can see what AI is doing in our pipelines, catch issues early and keep costs predictableAct as the go-to expert for AI-enabled engineering, coaching squads, running sessions and pairing with engineers to raise the bar across the teamKeep a close eye on the fast-moving AI tooling landscape, trial new capabilities and bring the best of them into day-to-day practiceApply an SRE lens to the systems underneath, owning monitoring, tracing and observability so we are first to know when something is (or is about to be) an issue, and can diagnose it quicklyDesign and improve CI/CD processes and pipelines using Git Actions, shaping our release process and deployment strategies so we consistently deliver high quality releasesPartner with engineers to troubleshoot build and deployment issues, support infrastructure engineering from design through to implementation, and unblock deliveryWhat we’d like you to bring A solid, demonstrable background in AI-assisted and agentic software engineering, going beyond personal use to shaping how a whole team works with it wellDeep hands-on experience with coding harnesses and agentic development tools (for example Claude Code, Copilot, Cursor), including configuration, extension and day-to-day use at scaleExperience designing evals, feedback loops and quality signals around AI-generated outputUnderstanding of AI agent architectures and how agentic systems apply to software engineering workflowsAwareness of the governance, guardrail, cost and observability considerations that come with LLM usage in a production engineering environmentA consultative, coaching style, with the ability to teach, pair and raise the bar across a team of experienced engineersComfort working with uncertainty and engineering forwards as the AI landscape continues to moveStrong knowledge of AWS and a good grasp of cloud engineering and architectural best practiceProven experience with CI/CD and configuration management tools, technologies and practices (ideally Git Actions)Hands-on experience with Infrastructure as Code, ideally Terraform, and with containerisation using Docker and orchestration with KubernetesWorking knowledge of NodeJS and TypeScriptUnderstanding of observability and monitoring, incident management, disaster recovery and security practiceSolid grounding in cloud and network security principles and technologies (TLS, OAuth2, Active Directory and similar)Experience with modern database engines (PostgreSQL/Aurora PostgreSQL, OpenSearch)Why Haven? You’ll be part of a forward-thinking, supportive community where ideas are valued, learning is encouraged, and the network you build will power memorable guest experiences for millions every year. At Haven, we’re one great team, united by our passion for creating amazing experiences for our guests and our people. You’ll have access to training, mentoring, and opportunities to grow your career in a supportive, forward-thinking environment. What’s In It For You? 25 Days Holiday + Bank Holidays + Holiday Buy SchemeAnnual bonus20% discount on both Haven and Warner Hotels holiday for you, family and friendsComprehensive wellbeing supportExclusive discounts with corporate partnersExciting career pathways, including Learning and Development opportunities such as Apprenticeships and DegreesEnhanced family friendly policies and pay (eligibility criteria applied)Who are we? We’re part of an award-winning Bourne Leisure family, which includes Haven & Warner Hotels. We have 9,000 fantastic team members and 39 beautiful seaside locations and our HQ based in Hemel Hempstead. What’s it like to work with us? Working with us is ultimately defined by our exceptional people and teams. At Haven, we take pride in our Breath of Fresh Air culture, which focuses on valuing and supporting every team member. We prioritise openness and transparency in our interactions allowing our team members to be their authentic selves. This is a remote-first role. You’ll work primarily from home, with occasional visits to our Hemel Hempstead HQ, on Park, or at external events as required. What can you expect during the recruitment process? The interview process will be up to 3 stages and may contain a presentation or skills test, depending on the role. If you require any support or reasonable adjustments to help you perform at your best during this process, please let us know. Diversity, equity, and inclusion are at the heart of who we are and what we do. Our commitment to these values is unwavering and they are central to our mission. We encourage applications from all backgrounds, communities and industries and we are happy to discuss any reasonable adjustments or flexibility that you may require, including whether a role can be part-time or a job-share. We genuinely care about every candidate’s experience during the recruitment process and are here to provide support where we can. If you require any assistance or reasonable adjustments while applying, please don’t hesitate to reach out to us at resourcingteam@bourne-leisure.co.uk.