QA Engineer, Voice AI Agents

Arbiter; New York, Northern (NY, KY); Hybrid; USD 180,000 - 200,000; Full time

Benefits offered by this job

Equity

PTO

Health insurance

Life insurance

Simple IRA

Development budget

Wellness program

Job summary

Arbiter, an AI-powered care orchestration company, is expanding its Agentic platform to optimize patient outcomes with multimodal AI approaches. We build scalable healthcare workflows and collaborate with clinical teams to deliver reliable, high-quality solutions.

As a QA Engineer reporting to the Head of Product, you will investigate conversations, transcripts, and logs to pinpoint root causes, while collaborating with engineers and deployment managers to fix issues and automate checks.

Qualifications

• 3–5 years in QA, support engineering, or similar on production software
• Strong debugging instinct and curiosity
• Comfort reading logs and querying data with SQL
• Experience writing test plans and bug reports trusted by engineers
• Clear written communication and precise documentation habits
• Good judgment on severity and prioritization during multiple issues

Responsibilities

• Investigate live campaign issues including dropped calls, wrong agent responses, failed handoffs, and data mismatches
• Trace problems across recordings, transcripts, logs, and configuration to identify root causes
• Write clear, reproducible bug reports with severity and impact
• Triage issues and route to correct owners (agent behavior vs. config/data/platform bugs)
• Run pre-launch QA on new campaigns and workflows
• Perform ongoing QA on live campaigns against defined quality standards
• Ensure campaigns behave as designed with correct targeting, sequencing, and outcomes
• Help build and maintain QA framework including test cases and regression suites
• Automate repetitive checks like transcript analysis and config validation

Skills

QA experience

Debugging instincts

SQL querying

APIs & JSON/YAML

Test plans & bug reports

Written communication

Severity prioritization

Tools

Observability tools

Call analytics tools

Log analysis tooling

Job description

Arbiter is the AI-powered care orchestration system that unites healthcare. We are launching our best-in-class, patient-facing Agentic platform to optimize patient outcomes through a unique multimodal approach. We optimize complex healthcare workflows that interface with patients using the latest Agentic AI approaches, and we combine it with a sophisticated platform to serve this Agentic layer at scale.

Backed by one of the largest seed rounds in health tech history and operators who bring the expertise and distribution to scale nationally, we're building the connected infrastructure healthcare should have had all along.

Our Culture & Values

We are a high-performing group of engineers dedicated to delivering innovative, high-quality solutions to our clients and business partners. We believe in:

• Excellence: Taking immense pride in our craft and the products we build, treating both with utmost respect and care.
• Impact-Driven Development: Firmly committed to engineering high-quality, fault-tolerant, and highly scalable systems that evolve seamlessly with business needs, minimizing disruption.
• Collaboration Over Ego: Valuing exceptional work and groundbreaking ideas above all else. We seek talented individuals who are accustomed to working in a fast-paced environment and are driven to ship often to achieve significant impact.
• Continuous Growth: Fostering an environment of continuous learning, mentorship, and professional development, where you can deepen your expertise and grow your career.

Responsibilities

As a QA Engineer reporting to the Head of Product, you will be the person who digs into calls and platform issues. You will review conversations, trace failures through transcripts, logs, and campaign configuration, find the root cause, and work with engineering and deployment teams to fix it. Work cross-functionally with engineers, deployment managers, and clinical and nurse operations staff. This role combines hands-on investigation, structured QA process, and growing automation.

Call and issue debugging:

• Investigate reported and detected issues on live campaigns, including dropped calls, wrong agent responses, failed handoffs, incorrect scheduling outcomes, and data mismatches.
• Trace problems across call recordings, transcripts, system logs, campaign configuration, and integration data to find the actual root cause.
• Write clear, reproducible bug reports that engineers can act on right away, with severity, member impact, and supporting evidence.
• Triage incoming issues, separating agent behavior from configuration errors, data problems, and platform bugs, and route each to the right owner.

Campaign QA:

• Run pre-launch QA on new campaigns and workflow changes: test scripts, edge cases, escalation paths, and handoffs to nurses or live staff.
• Carry out ongoing conversation QA on live campaigns against defined quality standards, and flag trends before they turn into customer issues.
• Check that campaigns behave as designed: correct targeting, sequencing, disposition logic, and outcome capture.

Process and automation:

• Help build and maintain the QA framework: test cases, scoring rubrics, regression suites, and release checklists.
• Automate repetitive checks where it makes sense, such as transcript analysis, config validation, and outcome reconciliation.
• Track quality metrics and report patterns to deployment, product, and engineering so issues get fixed at the source.

Minimum Qualifications

• 3 to 5 years in QA, support engineering, technical operations, or a similar role on a production software platform.
• A strong debugging instinct. You like finding out why something broke, and you don't stop at the first plausible answer.
• Comfort reading logs, querying data with SQL, and working with APIs and JSON or YAML configuration.
• Experience writing test plans and bug reports that engineers trust.
• Clear written communication and precise documentation habits.
• Good judgment on severity and prioritization when several issues are live at once.

Preferred Qualifications

• Experience with voice AI, conversational AI, IVR, or contact center platforms.
• Scripting ability in Python or similar for automating checks and analysis.
• Exposure to LLM evaluation, prompt testing, or conversation quality scoring.
• Healthcare experience, especially payer or provider outreach, and familiarity with HIPAA and PHI handling.
• Experience with observability tools or with call analytics tools.

This role will be remote or onsite in our New York City or Boca Raton office, a fast-paced, collaborative environment where great ideas move quickly from whiteboard to production.

Job Benefits

We offer a comprehensive and competitive benefits package designed to support your well-being and professional growth:

• Highly Competitive Salary & Equity Package: Designed to rival top FAANG compensation, including meaningful equity.
• Generous Paid Time Off (PTO): To ensure a healthy work-life balance.
• Comprehensive Health, Vision, and Dental Insurance: Robust coverage for you and your family.
• Life and Disability Insurance: Providing financial security.
• Simple IRA Matching: To support your long-term financial goals.
• Professional Development Budget: Support for conferences, courses, and certifications to fuel your continuous learning.
• Wellness Programs: Initiatives to support your physical and mental health.

Pay Transparency

The annual base salary range for this position is $180,000-$200,000. Actual compensation offered to the successful candidate may vary from the posted hiring range based on work experience, skill level, and other factors.