Senior AI-Driven QA Engineer – Eval Platform Lead

Valid8 Financial, Inc.; Austin (TX); On-site; USD 110,000 - 170,000; Full time

Job summary

Curative is building the future of health insurance with an AI-driven platform where engineers own what they ship. This Senior Software Test Engineer role focuses on evaluating agent-based code, creating regression suites, and testing real workflows with business stakeholders to ensure quality at speed.

You will own the eval harnesses, run end-to-end tests, investigate incidents, and push for precise, actionable fixes that improve production reliability in a fast-growing company.

Qualifications

• Minimum 5 years in software quality, testing, or engineering with automation experience.
• Fluency with LLM evaluation, datasets, and regression suites.
• Hands-on experience with AI agents and failure modes.

Responsibilities

• Own the eval platform, including datasets, graders, and CI integration.
• Conduct hands-on exploratory testing across end-to-end workflows.
• Validate we built the right thing by aligning with business stakeholders.
• Develop domain expertise to understand the end-to-end workflow.
• Produce production signals, bug hunts, and precise root-cause analysis.
• Exercise product judgment and help decide behavior when PMs are unavailable.
• Prioritize work under activity and risk pressure.

Skills

5+ years QA

LLM evaluation

AI agents

Job description

Curative is building the future of health insurance with an AI-driven platform where engineers own what they ship. This Senior Software Test Engineer role focuses on evaluating agent-based code, creating regression suites, and testing real workflows with business stakeholders to ensure quality at speed.

You will own the eval harnesses, run end-to-end tests, investigate incidents, and push for precise, actionable fixes that improve production reliability in a fast-growing company.