> Markdown version of [/jobs/ext/4692921-ai-prompt-agent-developer](https://www.wearedevelopers.com/jobs/ext/4692921-ai-prompt-agent-developer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# AI Prompt & Agent Developer

- **Company:** Recruiting from Scratch
- **Location:** San Francisco, CA, United States
- **Experience:** Experienced
- **Salary:** $90,000 - $130,000
- **Contract:** Permanent contract
- **Skills:** AI Evaluation, Artificial Intelligence, Automation of Tests, Big Data, Cognitive Science, Information Extraction, Python (Programming Language), Operational Databases, Twilio, TypeScript, Speech Recognition, Core Voice Platform, Chatbots, Large Language Models, Prompt Engineering, AI Coding Agents, Agentic-AI, Optimization Algorithms, Data Analytics, Speech Synthesis
- **Published:** November 12, 2026
- **Apply:** https://www.careerbuilder.com/job-details/ai-prompt-agent-developer-san-francisco-ca--6bcc6ad8-5eaf-4f12-96e3-32fd15e18fcc

## About the Role

Artificial Intelligence (AI), Artificial Intelligence (AI), Artificial Intelligence (AI) Agents, Voice Applications, Call Centers, Healthcare, Startup, Continuous Improvement, Analysis Skills, Performance Management, * 2+ years of professional experience in prompt engineering, conversational AI, or AI agent development.

 * Experience owning production prompt behavior for customer-facing AI systems.
 * Strong analytical skills with the ability to evaluate large datasets and identify behavioral improvements.
 * Excellent written communication and language intuition with strong attention to detail.
 * Familiarity with voice AI technologies, speech recognition (ASR), text-to-speech (TTS), or conversational AI platforms.
 * Comfortable reading Python and TypeScript code while collaborating closely with engineering teams.
 * Strong organizational skills with the ability to manage multiple experiments and deployments simultaneously.
 * Experience working in fast-paced startup environments with rapid iteration cycles.
 * Excellent cross-functional communication skills and customer-focused thinking.

Preferred

 * Experience building production AI agents serving thousands of users.
 * Background in linguistics, philosophy, law, cognitive science, or other language- and logic-intensive disciplines.
 * Experience with prompt evaluation frameworks, automated testing, or LLM optimization techniques.
 * Familiarity with telephony platforms such as Twilio or other voice infrastructure.
 * Experience working with healthcare workflows or enterprise AI products.
 * Strong understanding of LLM behavior, prompt engineering best practices, and AI evaluation methodologies.
 * Comfortable leveraging AI coding tools to accelerate development and experimentation.
 * Passion for building reliable, production-quality AI systems through continuous empirical improvement.

## Description

* Design, write, and maintain production prompts that power enterprise voice AI agents.
 * Own key components of agent behavior, including intent classification, information extraction, scheduling workflows, objection handling, and edge-case recovery.
 * Analyze production conversations daily to identify failure modes and continuously improve agent performance.
 * Build evaluation datasets, automated testing frameworks, and prompt optimization pipelines to validate behavioral improvements before deployment.
 * Develop and refine human-in-the-loop onboarding workflows that configure AI agents for new healthcare customers.
 * Design evaluation metrics that measure booking rates, automation success, and overall customer experience.
 * Collaborate closely with engineering teams to improve internal tooling, dashboards, and agent development workflows.
 * Conduct structured experiments to validate prompt changes using production data and measurable outcomes.
 * Help scale AI systems supporting millions of healthcare conversations while maintaining reliability and quality.
 * Continuously improve AI behavior through data-driven iteration and production monitoring.