Senior SDET / AI Quality Engineer- Remote in México

Job Description

We are looking for a Senior SDET / AI Quality Engineer to design, build, and evolve automation strategies for modern software platforms, including AI-powered and agentic applications. This role requires a strong engineering mindset, deep automation expertise, and the ability to drive quality across the entire software development lifecycle. Possess practical experience with automation frameworks, API testing, CI/CD quality practices, and emerging AI validation techniques. You will collaborate with engineering, product, and AI teams to ensure the reliability, correctness, security, and scalability of complex systems.

Responsibilities

• Design, develop, and maintain scalable automation frameworks for UI, API, integration, and end-to-end testing.
• Build automation solutions using modern testing frameworks and programming languages.
• Own quality engineering practices across the SDLC, from requirements validation to production monitoring.
• Develop automated test strategies for AI-powered applications, including agentic workflows, tool usage, decision paths, and failure scenarios.
• Validate AI system behavior across deterministic and non-deterministic scenarios.
• Create test approaches for LLM-based systems, including prompt validation, response quality evaluation, regression testing, and guardrail verification.
• Integrate automated testing into CI/CD pipelines and establish quality gates.
• Collaborate with developers and architects to improve system reliability, observability, and maintainability.
• Identify gaps in testing processes and proactively introduce improvements.
• Mentor engineers and promote automation and quality engineering best practices.

Must-Have Qualifications

• 5+ years of experience in Software Development Engineer in Test (SDET), Quality Engineering, or Automation Engineering roles.
• Strong automation engineering background with hands-on experience designing and maintaining test frameworks.
• Advanced experience with Playwright for UI automation and end-to-end testing.
• Strong API testing experience including REST APIs, integrations, contracts, and service validation.
• Experience creating automation pipelines integrated with CI/CD platforms.
• Strong programming skills in Java, Python, TypeScript, or similar languages.
• Experience building maintainable automation code using software engineering best practices.
• Experience testing distributed systems and complex application workflows.
• Experience testing AI-powered or agentic applications, including: workflow correctness validation, agent decision flows, tool/function calling validation, failure recovery scenarios, safety and reliability testing.
• Strong analytical skills with the ability to troubleshoot complex technical issues.
• Ownership mindset with the ability to independently drive quality initiatives.

Preferred Qualifications

• Experience with LLM evaluation frameworks and AI quality methodologies.
• Experience validating prompts, workflows, AI responses, and model behavior.
• Knowledge of AI guardrails, safety testing, and responsible AI practices.
• Experience testing retrieval-based systems (RAG), embeddings, vector search, and knowledge-grounded responses.
• Experience designing tests for non-deterministic systems.
• Exposure to performance, scalability, resilience, and chaos testing.
• Experience with observability testing, including logs, metrics, traces, and monitoring strategies.
• Experience with service virtualization, mocks, synthetic data generation, and test environment management.
• Experience testing cloud-native architectures and distributed/event-driven systems.
• Familiarity with platforms such as AWS, Azure, or GCP.
• Experience mentoring engineers and establishing QE standards across teams.

Technical Skills

• Automation & Testing: Playwright, Selenium/Cypress (plus), API automation frameworks, Contract testing