Location: Work-from-home
Working hours / Job Type: Monday to Friday, 9pm to 6am Manila time (9am to 6pm EST), with 8 core working hours exclusive of 1 hour break
Full time independent contractor position - you are responsible for your own taxes and mandated benefits
Company Profile:
Our client in the U.S. provides a 24/7 front desk solution built specifically for senior care. Home care agencies and post-acute facilities to instantly respond to every inquiry, automatically qualify leads, and schedule interviews, tours, and consultations directly onto the calendar—without adding workload to their teams.
As a QA Engineer, you will build and own the quality function across our AI-powered platform. You will be responsible for establishing testing practices from the ground up, covering both manual and automated testing across web applications and backend services. This is a foundational role with significant ownership and a direct impact on product quality.
Duties and Responsibilities
Design, build, and maintain a regression test suite covering both frontend and backend functionality
Perform structured manual testing across new features and existing workflows
Develop and maintain automated test suites using industry-standard frameworks
Build and execute automated tests for AI agent response quality, including accuracy, tone, and flow adherence
Produce regular test reports summarizing coverage, pass/fail rates, and outstanding defects
Collaborate with Engineering and Product teams to define acceptance criteria and test cases prior to development
Identify, document, and track defects through to resolution
Contribute to CI/CD pipeline integration for automated test execution
Must-have Skills / Qualification
5+ years of experience in software QA, with a mix of manual and automation testing
Hands-on experience building automated test suites using Playwright
Basic scripting experience using JavaScript, Python, or Java
Experience with API and backend testing (REST, Postman, or similar tools)
Familiarity with testing AI or LLM-generated outputs, including evaluation of response quality, prompt adherence, and edge case handling
Experience with prompt testing and LLM observability tools such as Langfuse, LangTrace, or similar platforms for tracing, evaluating, and monitoring AI responses
Ability to write clear, traceable test cases aligned with acceptance criteria
Strong written communication skills for test reporting and defect documentation
Experience working in Agile development environments
Advantageous or Nice-to-Have Skills/Experience
Experience testing conversational AI or chatbot platforms
Familiarity with healthcare or SaaS environments is a plus
Experience integrating automated tests into CI/CD pipelines (e.g., GitHub Actions, CircleCI, or similar tools)
Must have own equipment (laptop and stable internet connection)