AI-First QA Engineer

About the job

Opmed is a rapidly growing healthcare AI startup helping leading health systems optimize their operations. Our platform is already in use at major health systems and large networks. We are looking for a AI-First QA Engineer who will own product quality end-to-end - from hands-on exploratory testing to the automated suites that let us release with confidence.

What you'll do

• Own QA End-to-End: Own the entire QA lifecycle for product features, from acceptance criteria and test design through execution, automation, and release sign-off.
• Shape Acceptance Criteria: Partner with Product and Developers to refine acceptance criteria and make requirements testable before development starts.
• Build Playwright Automation: Design, build, and maintain reliable end-to-end automation frameworks with a strong focus on stability.
• Build AI-Powered Testing Workflows: Develop agentic workflows and LLM-driven pipelines for automated test generation, execution, failure analysis, and bug creation.
• 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/LLM-powered product features, including prompt behavior, output quality, and agent state management.
• Manual and API Testing: Perform manual and exploratory testing where automation is not the right fit, and test API and backend functionality, including data flows and integrations.

Requirements

• 3+ years of experience as a QA Engineer in a product company, with ownership of features from definition to release.
• 2+ years of hands-on experience building and maintaining automated test suites using Playwright.
• Solid grasp of QA methodologies (test plans, test cases, bug lifecycle, regression cycles), strong analytical skills, and attention to detail.
• Experience writing and refining acceptance criteria and working within a Definition of Done.
• Daily hands-on experience using AI tools such as Claude Code, Codex, or similar, applied to QA work.
• Experience integrating automation into CI/CD pipelines (GitHub Actions is a plus).
• Experience with API testing and SQL.
• Experience working in fast-paced, product-driven environments (startup experience is a plus).
• Fluent English.

Nice to have

• Experience with LLM evaluation frameworks or tooling (e.g. promptfoo, DeepEval, LangSmith).
• Experience testing data-heavy products or validating non-deterministic outputs.
• Experience in healthcare or other regulated domains.

Why join us At Opmed you will see your work deployed in real hospitals and health systems, improving the daily lives of clinicians and patients. You will be part of the heart of our technology, collaborate with a talented and mission driven team, and work with world class partners and health networks. If you want to build world class AI and optimization at scale and help shape the future of healthcare operations, we would love to talk.