[VCK] Senior QA Automation Engineer (AI Systems)

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 controls
• Validate audit logging completeness and document lifecycle traceability
• Build and maintain the incremental ingestion pipeline test suite
• Contribute to go/no-go decision packs: produce accuracy reports and test evidence documentation
• Tech Stack: Python, pytest, AWS, REST API Testing, Jira, Confluence
• Must-Have Skills & Experience
• +90% English written and oral (at least B2 level) with excellent communication skills
• 6+ years in QA automation engineering; senior seniority required
• Strong test automation engineering skills Python preferred (pytest or equivalent framework)
• Experience with API testing and contract testing
• Comfortable designing test frameworks for non-deterministic or probabilistic systems
• Experience in agile/scrum environments with Jira-based test management

Requirements

• Prior experience testing RAG systems, LLM outputs, or semantic search relevance this is a strong differentiator
• Familiarity with AI evaluation frameworks: RAGAS, TruLens, or custom rubric-based evaluation approaches
• Background in compliance-sensitive testing: audit trail validation, access control verification, or regulated-data environments
• We are accepting applications from LATAM countries

Additional Information

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. The platform is AWS-native with a Python/FastAPI backend, Vue.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 Match

How well this role fits your profile.

Company Intel

What employees say

Worked at Softwaremind? Share your experience