Kake

QA engineer for AI agentic workflows (manual)

In short

Senior manual QA engineer role focused on validating code changes and software behavior produced by an AI/agentic pipeline that generates fixes from customer support chat and voice transcripts. The job requires strong manual, exploratory, and regression testing skills across web, mobile, backend, and API layers, plus close collaboration with engineering and product teams. Candidates need 3+ years of relevant experience and should be comfortable with fast-paced, iterative environments; remote with 6–8 hours overlap with PST.

Tasks
•Manually test and validate code changes generated by an agentic pipeline that listens to customer friction from chat and voice support channels and produces code fixes from transcripts
•Collaborate with cross-functional teams to test wide-ranging code changes
•Perform exploratory testing, design test scenarios, and maintain confidence in production releases
Requirements
•Experience manually validating code changes and software behavior generated by automated or agentic workflows using customer support transcripts from chat and voice channels
•Ability to collaborate and communicate effectively across engineering and product teams
•Strong foundation in manual testing, exploratory testing, test case design, and end-to-end quality assurance across web, mobile, or backend applications
•Proactive, hands-on approach and ability to own functional quality end-to-end
•Ability to understand diverse application flows, identify edge cases, and perform comprehensive regression testing across complex multi-system environments
•Experience defining and executing detailed manual test plans for frontend UI changes, backend business logic, and API behavior, using tools such as Postman or browser developer tools
•Strong product sense and customer empathy to evaluate software behavior against real-world user friction and support scenarios
•Ability to adapt manual test coverage in fast-paced, dynamic environments with rapidly iterating feedback loops
•Excellent issue-tracking skills, including writing clear, reproducible bug reports and working with developers to resolve root causes
•High attention to detail and focus on minimizing production bugs and user impact
Nice to have
•Familiarity with test automation principles, scripting languages such as Python or JavaScript/TypeScript, or frameworks such as Playwright, Selenium, or Cypress
•Familiarity with AI/LLM-driven development workflows, agentic pipelines, or prompt-based code generation
•Experience analyzing support transcripts, customer service logs, or NLP outputs
•Exposure to CI/CD pipelines and continuous deployment workflows
•Background in event-driven architectures, microservices, or complex distributed systems
Conditions
•6–8 hours of overlap with PST

Stop applying.
Get referred.

$10 in free credits

In just 60 seconds, fully on autopilot — Eraldt's AI agents read your CV, map the roles you fit, find live vacancies and the people who can refer you, write personal emails, and get you referred.

This isn't an application: your CV doesn't go to the company, and we don't promise a referral for this exact role.

Discover who else lands interviews on autopilot