QA Engineer / Test Lead — Multimodal AI Platform - Freelance

**Location:** Fully remote (Canada) **Duration:** Milestone-based freelance contract **Hours:** Independent contractor engagement **Overview** An organization working with very large volumes of imagery, video, and audio is building a next-generation platform to help its experts make sense of it all. The platform is a modular, multimodal AI system that performs first-pass analysis automatically — computer vision on imagery and video, speech-to-text on audio, and language models for summarization and metadata — then hands its findings to human experts who review, correct, and approve before anything is finalized. This is a software architecture, integration, data-engineering, application, and secure-deployment effort that assembles best-in-class existing AI services into one robust production platform. You'll own quality for this modular, multimodal AI platform that turns imagery, video, and audio into structured, human-validated output. You define the test strategy, execute across every layer of the system, and produce the acceptance evidence that gets it signed off. This is a test-lead role with real breadth: functional and API testing, verifying the AI-plus-human review workflow, accessibility, performance at scale, and automated regression — plus the judgment to chase down issues wherever they surface across a distributed delivery team. **Key Responsibilities** - Define the test strategy and test plan, with traceability from each requirement to the test cases and evidence that prove it has been met - Design and execute functional, integration, end-to-end, and REST API tests across ingestion, AI-workflow orchestration, storage and retrieval, and the operator, administrator, and search applications - Verify the human-in-the-loop behavior — operator review, modify, approve and reject paths, workflow status and confidence display, and swapping one AI service for another without breaking the workflow - Run WCAG 2.1 AA accessibility verification (automated tooling plus manual keyboard and screen-reader testing) - Support performance and scalability testing against capacity and search-volume targets - Build and maintain automated regression coverage in CI/CD - Manage defects end to end — triage, ownership, and verified resolution - Produce the final test summary and acceptance-evidence package **Required Qualifications** - 5+ years in software quality assurance / test engineering, including ownership of a test program on at least one delivered system - Functional, integration, end-to-end, and REST API testing on production-bound systems, with requirement-to-test-case traceability - Test automation with an established framework (Playwright, Cypress, Selenium, or pytest) integrated into CI/CD - API and performance/load tooling experience (e.g., JMeter or k6) - Accessibility verification against WCAG 2.1 Level AA using both automated tooling and manual keyboard and screen-reader testing - Strong scripting/programming ability for test automation - Demonstrable track record on comparable systems (portfolio, case studies, or references) **Preferred Qualifications** - Experience testing systems that present machine-generated output for human review (confidence, provenance, and correction workflows) - Experience testing media-intensive or data-intensive systems - Experience testing software for government or regulated industries - Familiarity with containerized environments and CI/CD pipelines - Experience delivering complex software systems for government or regulated industries **Work Location & Requirements** - Fully remote position - Must be based in Canada and able to contract as an independent professional - Freelance / independent contractor engagement (not employment) - Selection process includes a review of background and past work, followed by a short technical assessment / exercise