Agentic Quality Engineering

At Lumenalta, we partner with forward-thinking organizations to build technology solutions that scale, delight users, and accelerate business growth. Our global teams bring curiosity, commitment, and technical excellence to every project. We value transparency, autonomy, and impact, empowering every team member to do their best work. We’re seeking an experienced Agentic Quality Engineer to own the quality and test strategy across a modern, AI-augmented engineering platform. This is a hands-on senior role responsible for defining quality standards, owning technical acceptance criteria, and supervising AI agent-led testing alongside human engineers #### Actively hiring We are hiring for a current opening on an active client project. This is a specific, presently open role. We review applications on a rolling basis and aim to move qualified candidates through our process promptly. #### About the role At Lumenalta, you will architect an AI-driven quality model rather than manage traditional QA. You set the standards, judgment, and guardrails, while AI agents handle test creation, maintenance (Playwright, Cypress, Jest), and triage alongside engineers. Your goal is to build these agents and ensure reliable, high-quality performance. #### What you will do * **Own the agent-led quality model**. Define how AI agents are directed, constrained, reviewed, and measured across the testing lifecycle and evolve that model as the capability matures. * **Orchestrate agents that build and maintain automation**. Direct Claude/ Codex, and Codex agents to create and maintain Playwright, Cypress, and Jest suites alongside engineers: generating coverage for new work, repairing suites as the product changes, and expanding depth where risk is highest. * **Develop the prompting, context, and workflow patterns** that make agent-generated tests reliable repo context strategies, guardrails, review gates, and the escalation paths for when an agent should hand back to a human. * **Set the quality and test strategy for the platform**, ensuring quality is engineered in at every stage rather than inspected in at the end. * **Drive adoption across engineering teams.** Onboard squads onto the model, document what works, run enablement, and make the practice self-sustaining without owning headcount. * **Own technical acceptance criteria** in partnership with Product Managers, and lead risk-based functional testing across all stages of development. * **Plan and manage UAT cycles**, environment specifications, execution, and stakeholder reporting. * **Establish the measurement framework.** Define quality KPIs that work for an agent-led model: coverage quality (not just coverage percentage), escaped-defect rates, agent output reliability, and human review load over time. * **Own service acceptance** for complex deliverables. * **Track where the frontier is moving.** Evaluate new agent capabilities, models, and testing technologies, and decide what earns a place in the platform. #### What we are looking for * Proven **leadership experience**, including managing others and working in cross-team and cross-organizational environments. * **Hands-on AI agent development and orchestration.** Practical, sustained experience directing Claude, Claude Code, Codex, or equivalent coding agents on real engineering work, not experimentation. You should be able to talk concretely about context management, prompt and workflow design, where agents fail, and how you designed around it. * **Experience supervising agents in a testing context** using them for coverage generation, defect detection, or suite maintenance, and applying real judgment to their output. * **Expert test automation proficiency with Playwright**, Cypress, and Jest (or close equivalents). You need to be able to read, judge, and fix what an agent produces. * **7+ years in QA or test engineering,** including setting strategy across multiple teams. * **Expert-level functional testing and UAT management.** * **Ability to define measurement frameworks and quality KPIs** from scratch, in a model where the traditional metrics do not fully apply. * **Solid engineering foundations:** microservices and API architecture, Git, JavaScript/TypeScript, Node/NPM. * **Expert familiarity with Jira, Confluence, Grafana, and Kibana.** * **Strong agile background and excellent English communication skills.** #### Nice to have * Anthropic Claude certification, or equivalent credentials in AI agent development or applied AI engineering * Public evidence of agent work: open-source contributions, published prompt or workflow patterns, talks, or writing on agent-led testing * ISTQB Advanced Level Test Manager certification * Professional certifications such as ITIL, BCS, ISACA, or ISC2 * Experience introducing a new engineering practice across an organization and getting it adopted #### Location This is a fully remote position; however, candidates must be based in regions that align with the UK time zone (GMT+1) to ensure effective collaboration with the client and team schedules. #### Application Deadline Applications will be accepted until **August 30, 2026**. Candidates can expect feedback by **September 7, 2026.**