Software Testing Lead

Key

Responsibilities Test Automation Strategy & Framework Design Design and implement scalable test automation frameworks for frontend (UI/UX), backend APIs, and AI/ML model-serving endpoints using tools like Selenium, Playwright, Postman, or custom Python/Java solutions. Build GenAI-specific test suites for validating prompt outputs, LLM-based chat interfaces, RAG systems, and vector search accuracy. Develop performance testing strategies for AI pipelines (e.g., model inference latency, resource utilization). Continuous Testing & CI/CD Integration Establish and maintain continuous testing pipelines integrated with GitHub Actions, Jenkins, or GitLab CI/CD. Implement shift-left testing by embedding automated checks into development workflows (e.g., unit tests, contract testing). AI/ML Model Validation Collaborate with data scientists to test AI/ML models for accuracy, fairness, stability, and bias mitigation using tools like TensorFlow Model Analysis or MLflow. Validate model drift and retraining pipelines to ensure consistent performance in production. Quality Metrics & Reporting Define and track KPIs. Test coverage (code, data, scenarios) Defect leakage rate Automation ROI (time saved vs. maintenance effort) Model accuracy thresholds Report risks and quality trends to stakeholders in sprint reviews. Drive adoption of AI-specific testing tools (e.g., LangChain for LLM testing, Great Expectations for data validation).

Soft Skills Strong problem-solving skills for balancing speed and quality in fast-paced AI development. Ability to communicate technical risks to non-technical stakeholders. Collaborative mindset to work with cross-functional teams (data scientists, ML engineers, DevOps).

Requirements Technical

Requirements Must-Have 10 years in test automation, with 2+ years validating AI/ML systems. Expertise in: Automation tools: Selenium, Playwright, Cypress, REST Assured, Locust/JMeter CI/CD: Jenkins, GitHub Actions, GitLab AI/ML testing: Model validation, drift detection, GenAI output evaluation Languages: Python, Java, or JavaScript

Certifications: ISTQB Advanced, CAST, or equivalent. Experience with MLOps tools: MLflow, Kubeflow, TFX Familiarity with vector databases (Pinecone, Milvus) and RAG workflows. Strong programming/scripting experience in JavaScript, Python, Java, or similar Experience with API testing, UI testing, and automated pipelines Understanding of AI/ML model testing, output evaluation, and non-deterministic behavior validation Experience with testing AI chatbots, LLM responses, prompt engineering outcomes, or AI fairness/bias Familiarity with MLOps pipelines and automated validation of model performance in production Exposure to Agile/Scrum methodology and tools like Azure Boards