Quality Assurance Engineer

Accountabilities: Build, maintain, and expand automated testing for AI-powered voice and chat agents, covering individual conversational turns through complete roleplay and end-to-end flows. Design and execute tests for LLM output quality, including correctness, consistency, structured outputs, language fidelity, prompt regressions, and other non-deterministic behaviors. Develop evaluation approaches using LLM-as-a-judge techniques, golden datasets, tolerance-based assertions, and other AI evaluation methodologies. Validate RAG pipelines, with particular attention to retrieval relevance, grounding, faithfulness, and overall answer quality. Test voice pipelines, including speech-to-text and text-to-speech accuracy, multilingual behavior, and real-time, low-latency performance. Automate testing across UI/E2E, API, database, AI-output, desktop, and mobile layers. Build and improve CI/CD quality processes, including linting, type checks, automated tests, AI evaluations, coverage gates, and deployment checks. Own release-quality activities, including regression strategies, early identification of defects, and evidence-based go/no-go recommendations. Take ownership of existing QA automation suites, improve their coverage and reliability, and establish stronger shared frameworks, tooling, processes, and QA standards. Support load and performance testing and continuously adapt quality practices as products, priorities, and technical challenges evolve. Requirements 5+ years of experience as a QA Automation Engineer, including proven hands-on experience testing AI-powered systems rather than only traditional software. Demonstrated ability to build testing frameworks, QA standards, and CI/CD-integrated automation from the ground up. Practical experience testing conversational AI, including voice and/or chat agents, in real-world production projects. Strong understanding of LLMs, prompt engineering, RAG, and approaches for testing and evaluating non-deterministic AI outputs. Knowledge of voice technologies and pipelines, including speech-to-text and text-to-speech, and experience automating their testing. Hands-on experience with LLM evaluation or observability tools such as Langfuse, LangSmith, DeepEval, or RAGAS. Strong proficiency in UI/E2E and API test automation, including tools such as Playwright, as well as experience creating or significantly improving CI/CD pipelines. Experience with database testing, load and performance testing, and desktop or mobile test automation. Strong Git practices, basic cloud knowledge, and familiarity with Agile development and sprint-based delivery. A pragmatic, hands-on approach and the ability to work effectively in fast-paced, rapidly changing environments. Strong problem-solving and ownership skills, with the ability to quickly understand unfamiliar systems and take initiative on new challenges. Familiarity with TypeScript is a plus, particularly for reading existing codebases and contributing directly to test and automation code. Additional valuable experience includes LiveKit or WebRTC, STT/TTS technologies such as Azure Speech, Google Cloud Speech, Deepgram, or Whisper, and AI/ML infrastructure such as vLLM, TGI, Triton, or Azure OpenAI. Experience with golden datasets, human-in-the-loop evaluation, Braintrust, Promptfoo, Cypress, Postman, AWS/Azure/GCP, Terraform, Pulumi, CloudFormation, Docker, or Kubernetes is also advantageous. Familiarity with product analytics, multilingual or localized testing, production monitoring, and error-tracking tools is a further plus. Benefits Fully remote working environment with the opportunity to work from India within a distributed APAC-focused team. Full-time position within an engineering organization working on AI-powered products. High level of ownership and autonomy over QA strategy, automation, evaluation, and release quality. Opportunity to work hands-on with advanced AI technologies, including LLMs, RAG, conversational agents, and voice pipelines. Direct impact on the quality, reliability, and customer readiness of AI products. Opportunity to build and evolve testing frameworks, evaluation systems, and CI/CD quality infrastructure from the ground up. Fast-paced environment offering exposure to emerging AI technologies and challenging quality problems. Collaborative work across Engineering, Product, and QA functions. Professional growth through ownership of complex, evolving technical challenges.