Full Description

We are looking for a highly skilled and motivated SDET to join our AI team. The team works on building cutting-edge AI features, including prompt engineering, generative AI, and other AI-driven capabilities. The ideal candidate brings strong expertise in test design, test methodologies, and test automation, along with a genuine interest in ensuring the quality and reliability of AI-powered products. This role involves close collaboration with stakeholders, developers, and cross-functional teams to deliver high-quality software solutions.

Key ResponsibilitiesTest Design and Execution Design, develop, and execute comprehensive test plans and test cases for AI-driven features, including prompt-based systems and generative AI models Apply strong testing methodologies such as boundary value analysis, equivalence partitioning, and related techniques to ensure robust coverage Identify edge cases and potential failure points in AI-based systems Test Automation Build and maintain scalable and reliable test automation frameworks using TypeScript (knowledge of other languages is acceptable) Automate regression, API, and end-to-end tests for AI features Integrate automated tests into CI/CD pipelines such as GitHub Actions Collaboration and Communication Work closely with stakeholders, developers, and data scientists to understand requirements and ensure testability of AI features Communicate test results, risks, and quality metrics clearly and effectively

AI and ML Testing Define and implement strategies for testing AI and ML-based features, including LLM outputs, prompt responses, and generative AI behavior Validate accuracy, consistency, reliability, and performance of AI models

Ownership and Problem Solving Take ownership of quality across AI features and proactively identify improvement areas Troubleshoot and debug issues across the stack to ensure timely resolution

Must Have Skills Strong expertise in test design and test methodologies Proven experience building and maintaining test automation frameworks Hands-on experience with Playwright, Selenium, or similar tools for UI and end-to-end testing Experience testing RESTful APIs and validating API contracts Familiarity with CI/CD pipelines, especially GitHub Actions Strong verbal and written communication skills General understanding of AI and ML concepts, including LLMs and generative AI Strong problem-solving mindset with the ability to think through edge cases and failure scenarios

Good-to-Have Skills Experience testing ML model-based features or LLM-driven systems Familiarity with prompt engineering and testing prompt-based workflows Experience with TypeScript or similar scripting languages Knowledge of agentic systems or AI-driven workflows Prior experience working in a startup environment

Traits We Value Customer-centric mindset with focus on user experience Curiosity and willingness to learn in a fast-evolving AI space High attention to detail and patience when testing complex systems Strong sense of ownership and accountability for quality