About Unframe
Unframe is an AI-first startup helping the world's largest enterprises bring LLM-powered applications to life in days - not months. We combine the speed of a product company with the flexibility of a consultancy, helping customers move from idea to deployed AI systems faster than anyone else in the market. With over $100M in TCV secured within 12 months, and a new $50M Series B led by Highland Europe, Unframe is rapidly scaling globally alongside Fortune 500 customers, backed by Bessemer, Craft, and TLV.
As an AI-First QA Automation Engineer, you'll build and scale Playwright automation while using AI tools and agents to transform how testing is developed and executed. You'll build reusable agent skills and workflows, configure agent environments, and optimize AI-assisted test generation, execution, failure analysis, and bug reporting. Working closely with Engineering, you'll help embed reliable AI-driven automation across the R&D lifecycle.
Responsibilities
•Build Playwright Automation: Design, build, and maintain reliable end-to-end automation frameworks with a strong focus on stability and low flakiness.
•Build and Optimize Testing Agents: Develop testing agents and their execution harnesses, including tool integrations, context management, and reusable skills. Evaluate and improve their reliability across test generation, execution, failure analysis, and bug reporting.
•Drive AI Adoption: Help QA and Engineering teams adopt effective AI workflows by building shared agent configurations, reusable skills, and practical guidance for everyday development and testing tasks.
•Integrate with CI/CD: Embed Playwright automation and AI-driven analysis into GitHub Actions and CI/CD pipelines, including automated test reporting and root cause analysis.
•Test AI Features: Develop strategies to validate AI-powered product features, including instruction following, output quality, tool use, and agent state management.
Requirements
•4+ years of hands-on experience as an Automation Engineer.
•2+ years of hands-on experience building and maintaining automated test suites using Playwright.
•Strong programming skills in TypeScript or Python.
•Proven experience configuring, extending, and optimizing AI agents for development or testing workflows, including agent harnesses, context management, reusable skills, and tool integrations.
•Experience building AI-powered workflows using LLMs, prompt and context engineering, and agent orchestration.
•A practical understanding of LLM capabilities and trade-offs, with the ability to select models and configure agents for different tasks.
•Experience integrating automation into CI/CD pipelines (GitHub Actions is a plus).
•Experience working in fast-paced, product-driven environments (startup experience is a plus).
Conditions
•Real ownership from day one. Drive decisions, shape ideas and make them work.
•Your fastest learning years. Build alongside founders and VPs in a space that moves weekly.
•You'll have the opportunity to write and build what comes next.
