Senior Software Test Engineer
Posted 1ds ago
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
Senior Software Test Engineer building AI-agent evaluation infrastructure and testing workflows for Curative’s health insurance platform. Debugging production failures and partnering with business teams to improve quality.
Responsibilities:
- Build and maintain the eval platform, including harnesses, datasets, graders, and CI integration
- Measure agent behavior through task success, tool-use correctness, drift, latency, and cost
- Perform hands-on exploratory end-to-end testing based on how members, operations teams, and providers use the product
- Work with business stakeholders to understand real workflows and validate that the right product was built
- Develop domain expertise in Curative’s business workflows
- Use traces, failure taxonomies, and dashboards to turn agent issues into specific findings
- Reproduce production failures, identify root causes, fix issues, or provide precise diagnoses
- Advise on quality concerns and make product behavior or requirements decisions when needed
- Prioritize testing and quality work according to risk and business impact
- Review AI-generated code changes and maintain quality standards
Requirements:
- 5+ years in software quality, testing, or engineering with real range
- Experience writing automation and performing serious exploratory testing
- Fluency with LLM evaluation, including golden datasets, LLM-as-judge, programmatic graders, and regression suites for prompts and agent loops
- Hands-on experience with AI agents and failure modes including silent drift, tool misuse, and compounding errors
- Debugging depth with logs, traces, queries, and production forensics
- Ability to fix bugs in Python or TypeScript
- Ability to work with non-technical business stakeholders and operations leads
- Comfort with ambiguity, speed, and working without mature processes or sprint boundaries
- Pragmatic quality judgment
- Sharp written communication
- Claude Code, Cursor, or equivalent as a primary development tool
- Uses AI to accelerate quality work while recognizing the limits of AI judgment
- Reviews every AI-generated diff and does not merge on vibes
- Strongly preferred: experience standing up eval or observability infrastructure from zero
- Strongly preferred: LLM observability tooling such as LangSmith, Braintrust, Arize, or homegrown tools
- Strongly preferred: defining unsupervised agent capabilities and building guardrails
- Strongly preferred: product requirements and behavior definition experience
- Strongly preferred: building deep domain expertise in a complex operational business
Benefits:
- Curative Health Plan (100% employer-covered medical premiums for you and 50% coverage for dependents on the base plan.)
- $0 copays and $0 deductibles (with completion of our Baseline Visit)
- Preventive and primary care built in
- Mental health support
- One-on-one care navigation
- Chronic condition programs (diabetes, weight, hypertension)
- Maternity and family planning support
- 24/7/365 Curative Telehealth
- Pharmacy benefits
- Comprehensive dental and vision coverage
- Employer-provided life and disability coverage with additional supplemental options
- Flexible spending accounts
- Generous PTO policy plus 11 paid annual company holidays
- 401K for full-time employees
- Generous up to 8–12 weeks paid parental leave, based on role eligibility














