AI Prompt and Agent Engineer \- San Francisco, CA

Schedule: In office, five days per week

Work Authorization: US citizens and Green Card holders only

Role Overview

A rapidly scaling AI operations platform supporting more than one thousand healthcare locations is expanding its engineering team. The company processes tens of millions of phone calls and text interactions and is building advanced AI systems that power real time communication, scheduling, and operational workflows for healthcare practices. This team is hiring multiple AI Prompt and Agent Engineers who can shape the behavior, reliability, and intelligence of production grade AI systems used at significant scale.

This role is ideal for someone who has already worked on AI driven products with real users, understands how to tune and refine model behavior, and enjoys the blend of experimentation, evaluation, and hands on engineering. You will work closely with product, engineering, and operations teams to ensure the AI behaves accurately, safely, and consistently across a wide range of real world scenarios.

Responsibilities

• Design, refine, and maintain prompt architectures and agent workflows that power real time phone and text interactions.
• Own the behavior, tone, accuracy, and reliability of AI driven communication systems.
• Develop evaluation frameworks to measure model quality, correctness, and user experience.
• Curate, label, and structure datasets used for training, fine tuning, and continuous improvement. Conduct error analysis and root cause investigations to improve model performance. Collaborate with engineering teams to integrate prompts, tools, and agent logic into production systems.
• Work closely with product teams to translate operational needs into AI behavior and decision making.
• Test and validate AI outputs to ensure alignment with healthcare communication standards and compliance requirements.
• Monitor live system performance and identify opportunities for optimization and refinement.
• Contribute to internal documentation, guidelines, and best practices for prompt engineering and agent design.

Ideal Background

• Experience building or maintaining AI systems used by more than one thousand users.
• Hands on experience with prompt engineering, agent design, or ownership of AI product behavior.
• Strong understanding of LLM behavior, context management, and evaluation techniques.
• Experience with data curation, dataset quality review, and annotation workflows.
• Comfort working in fast paced, high growth environments where experimentation and iteration are part of the daily workflow.
• Strong communication skills and the ability to collaborate with cross functional teams.
• If not a native US English speaker, a strong grasp of American English and cultural context is required, ideally supported by prior work in US customer facing environments or relevant academic background.

Who Will Thrive Here

• Someone who enjoys shaping how AI behaves in the real world.
• Someone who is comfortable owning outcomes and improving systems through rapid iteration.
• Someone who can balance creativity with structure, and experimentation with reliability.
• Someone who is energized by building in person with a highly collaborative team.

Compensation and Benefits

• Competitive salary and equity package.
• Comprehensive health benefits.
• Opportunities for rapid growth within a scaling AI organization.
• A collaborative, in person culture focused on building high impact technology.