Qualifications

• 2+ years experience with LLM or agent systems, covering professional, personal, and research work.
• Hands-on experience with tools like evaluations, retrieval, and integrations in agent infrastructure.
• Proficient in Python or a similar systems programming language.
• Strong fundamentals in computer science and mathematics, with academic credentials being a plus.
• History of diagnosing issues in production LLM or agent systems within tech environments.
• Ability to recognize and automate repetitive tasks with coding solutions.
• Demonstrated warmth and empathy in patient interactions, adept at managing difficult conversations.
• Self-starter comfortable in a low-structure, startup environment.
• Familiarity with prompt engineering and AI model evaluation is advantageous.
• Experience in healthcare AI systems is also beneficial.

Responsibilities

• Diagnose failures in patient AI conversations and implement code fixes.
• Develop and maintain agent infrastructure with system integrations and evaluation frameworks.
• Automate routine manual workflows in clinics to reduce operational toil.
• Manage patient interactions empathetically when AI fails, gaining product insights.
• Maintain ownership of entire systems with minimal supervision, making independent architectural decisions.

Benefits

• Opportunity to impact patient outcomes directly through AI technology.
• Work within a small, senior team that values collaboration and innovation.
• Engage in a high-autonomy work environment fostering personal and professional growth.
• Full-time role located in the vibrant tech scene of San Francisco.