Enterprise AI platform automating voice sales conversations for healthcare organizations
AI Prompt & Agent Developer
You'll spend mornings debugging why a clinical-recruiting agent mispronounced 'anesthesiology,' then afternoons rewriting system prompts until phone calls pass for human. It's QA as forensic work: listening to recordings, tracing failure trees through Python pipelines, and stress-testing voice agents against edge cases no one predicted. The goal isn't coverage metrics—it's call quality that keeps hospitals from hanging up.
What we're looking for
- 2+ years building or testing LLM-powered applications, with direct prompt-engineering experience
- Proficiency in Python and TypeScript for writing test harnesses and debugging agent logic
- Demonstrated ability to evaluate conversational AI quality beyond automated metrics—listening, scoring, iterating
- Familiarity with healthcare compliance constraints or regulated-industry QA standards
- On-site in San Francisco, working alongside voice engineers and sales teams in tight feedback loops
- Must be based in the United States.