Agent Deployment Engineer (Residency Program)

About this role

Hippocratic AI seeks an Agent Deployment Engineer to develop and optimize prompts for healthcare conversations using their safety-focused LLM platform. You'll work cross-functionally with engineers, product managers, and clinicians to build autonomous clinical dialogue systems, combining software engineering with advanced prompting techniques.

What you'll do

• Design and iterate complex prompts for the conversation planning layer to enable agentic workflows
• Collaborate with product, engineering, and clinical teams to create fully autonomous patient conversations
• Experiment with and analyze LLM outputs to refine prompt strategies and improve clinical safety
• Apply advanced prompting techniques to optimize model performance and patient experience
• Configure and test prompts to ensure engaging, clinically appropriate interactions
• Conduct outcome analysis to drive continuous improvement in conversation quality

What they're looking for

• Python programming
• LLM prompting (ChatGPT, Claude, etc.)
• Database design and querying
• RESTful API development
• Problem-solving and experimentation
• Backend development frameworks (Flask, Django, Spring Boot)
• AI/ML concepts
• Data privacy and security practices

Benefits

• Work on transformative healthcare AI technology
• Collaborate with experts from Stanford, Google, Meta, NVIDIA, and leading hospitals
• Join a well-funded company ($404M total, $3.5B valuation)
• Five-day in-office requirement in Palo Alto supporting team culture

Likely interview questions

• Walk us through your experience with LLM prompting (ChatGPT, Claude, etc.). Can you describe a specific project where you optimized prompts and what metrics you used to measure success?
• Tell us about a time you collaborated with non-technical stakeholders (like product or domain experts). How did you translate their requirements into technical solutions?