[VCK] Senior QA Automation Engineer (AI Systems)

Аналитика рынка

Стек

Откликнуться

Загрузите резюме — мы свяжем вас с работодателем напрямую через нашу базу.

Описание

We are Software Mind, an awesome team of engineers who are ready to ramp up any top-notch company’s projects! Our aim? To always be one step ahead. Become part of a multicultural company in constant growth with an excellent work environment certified by Great Place To Work! About the Project Software Mind is building a private, tenant-isolated AI assistant for the real estate title and settlement industry. The platform is a retrieval-first (RAG) system that ingests historical email, documents, and structured metadata into a per-tenant vector index, and serves grounded, cited, expert-weighted answers through a chat-style Q&A interface with single sign-on and full audit logging. js frontend, OpenSearch/Pinecone vector store, and OpenAI/Anthropic/Bedrock as LLM provider. You will join a senior, cross-functional LATAM-based team where hands-on AI delivery experience not just familiarity is the baseline expectation. You build the validation harness that determines whether the AI system meets accuracy standards this is your primary deliverable. This is not generic test automation. You need to understand what 'correct' means for a RAG-based retrieval system and design test frameworks that can surface retrieval failures, hallucinated citations, confidence score drift, and RBAC access violations. Your Responsibilities Design and implement the validation harness for RAG output quality: retrieval accuracy, citation correctness, and grounding Build automated test suites for the AI Extraction Gateway across Simple RAG and Complex RAG implementations Develop and execute accuracy rubric test cases in collaboration with the BA and Designated Subject Matter Expert Automate regression testing for confidence score calibration and source weighting behaviour Test RBAC enforcement and role-specific filtered view access cont

Контакты работодателя (email/phone/telegram) скрыты из публичного превью — отправьте резюме, чтобы мы связали вас напрямую.