SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Togal.AI is seeking an experienced AI QA Engineer / Test Architect to own quality strategy end-to-end for an AI-powered cloud platform serving the construction industry. This role combines traditional QA expertise with cutting-edge AI/LLM testing, positioning you as the quality voice shaping how the company measures product excellence.
You will define and implement testing standards across functional, non-functional, and AI-specific dimensions, embedding quality from requirements through production. Key responsibilities include building and maintaining non-functional test automation (performance, load, stress tests using k6, JMeter, Gatling) integrated into CI/CD pipelines with quality gates. You'll design and operate LLM/AI evaluation frameworks using tools like DeepEval and Langfuse to assess AI feature quality across accuracy, hallucination rate, relevance, faithfulness, and safety metrics.
You'll test AI features and agentic behaviors by validating non-deterministic outputs, prompt variability, model regression, guardrail enforcement, and multi-step agent task-completion rates. You'll champion shift-left testing practices, embedding QA into planning and design reviews to catch defects before coding. As a quality advocate across engineering, product, and AI teams, you'll drive a quality engineering culture through blameless post-mortems, visible metrics, and reliability standards.
You'll accelerate delivery using AI-assisted tooling, self-healing automation, and intelligent test prioritization. You'll build observability into production by defining and monitoring post-release quality signals, model drift indicators, and SLO thresholds to distinguish regressions from expected non-determinism.
Must-haves include solid traditional QA foundations (test planning, case design, functional/regression/exploratory testing, defect lifecycle), deep test automation expertise with modern frameworks (Playwright, Cypress) and TypeScript or Python, hands-on non-functional test automation experience, practical AI/LLM testing literacy, working knowledge of eval frameworks, CI/CD integration experience, quality ownership mentality, and understanding of microservices and API testing. Nice-to-haves include agentic systems testing, AIOps/MLOps/LLMOps familiarity, accessibility/security testing, red teaming experience, and startup environment background.
