Test Lead (AI Validation & Integration)

Employment: contract Experience: senior executive Salary: 222000 to 362400 PLN per year We are looking for an experienced Test Lead to drive the Quality and Validation strategy for a high-impact solution, in a highly regulated industry, involving AI components and Salesforce integration. In this role, you will own both definition and delivery of the Testing & AI Validation Strategy. You will be responsible for defining how solution outputs are verified for correctness, reliability, and safe operation, bridging the gap between newly developed AI Agents components and the client’s Salesforce environment. What you’ll do Strategy & Planning: Own the QA Strategy: Design, plan and dDevelop the comprehensive Testing and AI Validation Strategy, covering FunctionalUnit, E2E, Integration, Regression, and User Acceptance Testing (UAT). Address NFR and align against standards (e.g. GDPR, HIPAA, HITRUST, etc.) AI Validation Logic: Define validation plans for AI components, specifically determining what constitutes "correct" output, setting success thresholds, and establishing evaluation methods (including handling hallucinations and grounding rules). Environment & Data: Create detailed plans for Test Environments (Dev/Test/Prod) and define the Test Data Strategy to ensure sufficient coverage for standard scenarios, edge cases, and ingestion failures. Execution & Reporting: Hands-on Testing: Execute functional, regression, exploratory, performance, and load tests. Integration Coordination: Coordinate "Joint End-to-End Validation" efforts, collaborating with the client team to manage testing of Salesforce integration Pipeline Integration: Integrate testing activities into the CI/CD pipeline for continuous quality assurance Process Management: Manage Jira test case structures aligned to user stories and acceptance criteria Metrics: Provide regular reporting, tracking key QA metrics such as defect ratios About the project, in short. Is it a new project or maintenance? This is a new project for a client that we have already established collaboration with during other projects. We are finalizing the Discovery Phase for this project and moving into Delivery. We are developing a data validation and automation engine that processes structured and unstructured inputs against a complex logic framework. The system utilizes AI models to interpret user-submitted data, identifying discrepancies and missing information before mapping the results to a structured output format. Key components include automated ingestion, rule-based validation logic, and integration with existing enterprise architecture in a highly regulated industry. Technical Requirements (must-have): Fluent English QA Strategy: Experience defining end-to-end testing strategies for complex solutions End-to-End Testing: Experience in designing and executing E2E tests for complex, integrated systems using any modern testing technology AI/ML/LLM Testing Experience: Proven ability to validate AI models Test Data Management: Experience strategizing and managing test data across multiple environments (Dev/Test/Prod) Traceability mindset: linking requirements → test cases → evidence → defects → release decisions. Experience testing NFRs: performance, reliability, auditability, security basics. Strong understanding of privacy and sensitive data handling in testing (PII/PHI minimization, masking/anonymization) Hands-on automation experience (at least one strong stack): e.g., Python/Java/JS + frameworks (pytest/JUnit/etc.) QA Metrics: Ability to track and report on specific QA metrics, such as defect ratios Good communication skills (written and verbal) Jira Proficiency Full time availability, with overlap during 14:00-18:00 - to ensure seamless collaboration with USA based client Additional Requirements (nice-to-have): Familiar with AWS platform ISTQB or similar certifications Previous experience in fast-paced consulting or client-facing projects