Sr. SDET - LATAM (Remote)

Luxury Presence is building the AI growth platform for real estate. Backed by Bessemer Venture Partners and other top investors, we're a Series C company on track to hit $100M in annual recurring revenue in the next six months. More than 87,000 real estate professionals, including over 30% of the WSJ Real Trends top 100 agents in the United States, use us to run and grow their business. As a Senior Software Development Engineer in Test (SDET), you will lead the design and evolution of Luxury Presence’s next-generation test automation strategy that merges traditional test engineering with AI-augmented quality intelligence. You’ll own the architecture and development of scalable test frameworks, introduce AI-enabled test generation and validation, and build custom Model Context Protocol (MCP) tools to supercharge Playwright testing. You’ll collaborate with engineering and AI teams to test AI agents, LLM-integrated features, and AI-driven customer experiences. Key Responsibilities * Architect and evolve end-to-end automated testing frameworks, with Playwright as the core automation technology. * Lead the integration of AI-enabled testing methodologies into the SDLC, including predictive test selection, LLM-based test case generation, and self-healing automation. * Design, build, and maintain custom MCP (Model Context Protocol) servers and tools that enhance Playwright’s context-awareness and adaptability. * Develop test strategies for AI agents and AI-integrated product features, ensuring accuracy, reliability, and safety. * Partner with AI/ML engineers to define validation frameworks for AI model performance, prompt correctness, and deterministic output behavior. * Mentor SDETs and QA engineers on advanced automation, AI-assisted testing, and test strategy best practices. * Define quality metrics and feedback loops for intelligent CI/CD pipelines, enabling faster, safer releases. * Collaborate cross-functionally with Product, DevOps, and Architecture to embed testing standards and ensure high quality across all delivery stages. * Stay ahead of emerging AI testing frameworks and champion innovative approaches to improve testing scalability and precision. What You’ll Bring * 7+ years of experience in software testing, test automation, or software engineering, including 2+ years in a technical leadership capacity. * Proven expertise in Playwright (or similar tools like Cypress, Selenium, or WebDriverIO) and TypeScript/JavaScript programming. * Demonstrated success integrating AI systems or tools into QA workflows, including prompt engineering, test generation, or defect analysis using AI models. * Hands-on experience testing AI-driven solutions, LLM-based systems, or AI agents. * Experience designing and maintaining test automation frameworks for scalability, reliability, and observability. * Deep understanding of CI/CD pipelines (GitHub Actions, Jenkins, GitLab, CircleCI) and cloud-native environments (AWS, Kubernetes). * Familiarity with GraphQL, Apollo, React, and microservice-based architectures. * Strong mentorship, communication, and collaboration skills. * Passion for innovation, particularly in AI, automation, and developer productivity. Technology Stack * Frontend: React, GraphQL, Apollo * Backend: Node.js, TypeScript, Microservices * Database: Postgres, Redis, DynamoDB * Cloud: AWS, Kubernetes, Lambda * Testing: Playwright, Jest, Custom MCP tools * CI/CD: GitHub Actions, CircleCI, Jenkins, ArgoCD * AI & Automation: AI agents for QA, AI-assisted test generation, model validation frameworks, prompt-based testing utilities Nice to Haves * Experience developing or testing AI agents (autonomous or semi-autonomous assistants). * Knowledge of LangChain, LlamaIndex, or other orchestration frameworks for testing LLM applications. * Experience with AI model testing (data drift, regression analysis, hallucination detection). * Familiarity with model observability and quality metrics for LLM-based products. * Exposure to mobile testing (React Native, Appium, Maestro). * Experience leading QA or automation teams or owning large-scale test infrastructure.