Senior AI Test Engineer, QA

• Architect and implement a Retrieval-Augmented Generation (RAG)-based test automation framework using local LLMs (e.g., Ollama).
• Build intelligent systems capable of reasoning about test requirements, analyzing app states, and generating dynamic test scenarios.
• Develop AI-powered screenshot analyzers using Computer Vision (OpenCV) and OCR for precise UI validation.
• Automate localization testing across languages and screen sizes using AI models to validate text, layout, and formatting.
• Train models to detect UI anomalies, visual regressions, and inconsistencies beyond the scope of traditional tools.

• Design and develop a Python-based HIL framework for testing mobile apps integrated with proprietary medical hardware.
• Build communication interfaces (USB, Bluetooth, Serial) to control and monitor device interactions during automated tests.
• Train and deploy AI models that adapt to the unique behaviors of hardware interfaces for end-to-end system testing.

• Deploy and manage local infrastructure for AI model inference, ensuring high performance and data privacy.
• Containerize models and automation agents using Docker and integrate them into CI/CD pipelines (e.g., Jenkins, GitLab CI).
• Build continuous learning loops that leverage test results and failure data to retrain and improve AI models.

• Utilize open-source AI/ML libraries such as PyTorch, TensorFlow, Hugging Face, and scikit-learn for model development.
• Extend or replace traditional frameworks like Appium with custom AI-assisted components.
• Develop Python-based tooling for model training, inference, and integration into test workflows.

• 4+ years of hands-on experience in software development with a strong focus on Python and AI/ML applications.
• Proven expertise in building and fine-tuning models using PyTorch, TensorFlow, or Hugging Face.
• Demonstrable experience with Computer Vision (OpenCV) and OCR for visual analysis and UI validation.
• Strong background in building test automation frameworks and a clear understanding of the limitations of traditional tools like Appium.
• Experience with CI/CD, Docker, and deploying ML models into production or testing environments.

• Hands-on experience with local LLMs (e.g., Ollama, Llama.cpp) and RAG systems using LangChain or LlamaIndex.
• Prior experience with Hardware-in-the-Loop (HIL) or Software-in-the-Loop (SIL) testing.
• Familiarity with mobile development and testing ecosystems (Android/iOS).

• A builder's mindset with a drive to create innovative solutions.
• Excellent problem-solving skills and the ability to navigate ambiguity.
• Strong sense of ownership and ability to work independently.
• Fluent and effective communication skills in English.

WS Audiology