You’ll be the first Quality Engineer in a newly formed Public Claims team, reporting to Dale Hurley, Head of Agentic AI Engineering, working on the delivery of agentic AI products directed by the founder of ATI Group, global LegalTech leader Christian Beck.
You’ll design and build the quality foundations that let a small team of AI-augmented engineers keep moving at pace while shipping products that inhouse lawyers trust with their work.
Partner directly with engineers to build the testing strategy, tooling, and automation that matches an AI-assisted development workflow.
Design and implement evaluation frameworks for agentic and generative AI features – regression suites for prompts, models, retrieval quality, tool use, and end-to-end agent behaviour.
Own the automated test stack across unit, integration, contract, and end-to-end layers, making pragmatic calls on coverage, tooling, and where human review still matters most.
Build the CI/CD quality gates that let the team ship multiple times a day without breaking customer trust – pre-merge checks, canary strategies, and production observability for AI behaviour.
Establish the feedback loops between production signals (errors, user corrections, eval drift, cost and latency regressions) and the development cycle so the team learns fast and fixes faster.
Shape how the team uses AI-assisted coding tools safely – spotting the failure modes (plausible-but-wrong code, missing edge cases, silent regressions) and building the guardrails that catch them.
Present your thoughts, findings, and progress clearly and confidently to internal teams and leadership.
Requirements
You’ve shipped quality frameworks for products that went from zero to thousands of users, on small, fast-moving teams where you had to build the tooling yourself rather than hand specs to a QA team.
Hands-on experience testing Generative AI or agentic systems in production – evals, LLM-as-judge, golden datasets, regression detection on non-deterministic output, cost and latency budgets, safety and hallucination checks. You’ve seen AI products break in ways traditional QA doesn’t catch, and you know how to catch them.
Deep fluency with modern test automation – unit, integration, contract, and end-to-end – across cloud services, APIs, and data pipelines. You write code, not just test plans.
You’ve worked on teams using AI-assisted coding (Claude Code, Cursor, Copilot, or similar) and have opinions on how quality practices need to adapt when humans are reviewing AI-generated code at volume.
Even better if you have: Experience in process-heavy workflows, or SaaS
Experience testing scraping automation, or structured extraction systems where correctness really matters
Experience in internal venture studios, innovation teams, startups, or product incubation environments
Background building out QE practice as the first quality hire on a team.
Tech Stack
Cloud
Benefits
Your work matters. We solve real world problems that improve and support local, everyday law firms. So they can do their best work for the people in the communities they serve.
Make an impact. You won’t be another ‘cog in the wheel’ here. We give full trust and autonomy for you to be heard, to work on big & complex projects – and to make a real difference.
Work with a group of authentic, passionate people who love what they do.
Well-funded and global. CORTO is part of ATI Global – one of the largest international LegalTech companies.
Flexible and hybrid working. We engage, share, and collaborate on ideas and workflows.
Career and learning opportunities
we move fast and need smart people to get us where we're going. We are a scaling business and looking for people who want to grow with us.
Have fun with us. Celebrations. Socials. Sports teams. Access to sailing and yacht events.
We value your well-being with additional time off, gym membership and other perks.
Fast-paced tech environment, if we don't disrupt ourselves someone else will do it!
Access to LEAP Home
a program unique to the ATI Group to support you in buying your primary residence.