Senior Agent Engineer
Posted on July 27, 2025 (about 1 month ago)
About Us
Hippocratic AI is developing the first safety-focused Large Language Model (LLM) for healthcare. Our mission is to dramatically improve healthcare accessibility and outcomes by bringing deep healthcare expertise to every person. No other technology has the potential for this level of global impact on health.
Why Join Our Team
- Innovative mission: We are creating a safe, healthcare-focused LLM that can transform health outcomes on a global scale.
- Visionary leadership: Hippocratic AI was co-founded by CEO Munjal Shah alongside physicians, hospital administrators, healthcare professionals, and AI researchers from top institutions including El Camino Health, Johns Hopkins, Washington University in St. Louis, Stanford, Google, Meta, Microsoft and NVIDIA.
- Strategic investors: We have raised a total of $278 million in funding, backed by top investors such as Andreessen Horowitz, General Catalyst, Kleiner Perkins, NVIDIA’s NVentures, Premji Invest, SV Angel, and six health systems.
- Team and expertise: We are working with top experts in healthcare and artificial intelligence to ensure the safety and efficacy of our technology.
For more information, visit www.HippocraticAI.com.
We value in-person teamwork and believe the best ideas happen together. Our team is expected to be in the office five days a week in Palo Alto, CA unless explicitly noted otherwise in the job description.
About the Role
We are looking for an AI Agent Engineer to bend language models to their will. In this role, you will collaborate with engineers and research scientists to enhance the effectiveness and safety of generative AI solutions by designing, testing, and improving prompts that drive clinical safety and patient experience. You will also create automations to test your creations. An ideal candidate is equal parts software engineer and prompt engineer, product, loves experimentation and tinkering, is extremely thorough and detail oriented, and has a passion for conversation and communication.
Responsibilities
- Help achieve world class performance on several safety-critical LLM applications
- Collaborate with product managers to write detailed product specs for how models should behave
- Help design agentic model workflows
- Use advanced prompting techniques to develop and optimize prompts for language models to improve model performance, clinical safety, and patient experience.
- Contribute to automated model testing and evaluation infrastructure
- Build automations to create and select the best prompts for any given task
- Conduct experiments and analyze outcomes of model outputs to refine and iterate on prompt strategies.
- Write and configure prompts to create engaging, patient-oriented conversations
Required Qualifications
- Experience (5+ years) in a technical or semi-technical field, such as engineering, analytics, data science, or product management
- Demonstrated product sense and intuition for conversation design
- Proficiency writing simple scripts in Python
- Familiarity with basic principles of machine learning, conversational AI, and Large Language Models
Preferred Skills
- Experience developing, designing, and/or interacting with non-deterministic AI/ML systems
- Experience designing and conducting experiments and statistical analysis, specifically measuring and optimizing the accuracy of model outputs
- Experience with written language, communications and/or conversation design
- Software engineering experience
Candidate Background
Given that the field of prompt engineering is very new, we understand that it’s unlikely that you will have direct experience on your resume. While direct experience in prompt engineering is not expected, we value transferable skills that align with the responsibilities of the position. Ideal candidates might come from various related fields where they have honed relevant skills in problem-solving, analytical thinking, and written communication.
You might be a good fit if you have an engineering background and have or are looking to move into a product role. Perhaps you’re a data scientist who writes on the side. Or maybe you are a conversation designer who dabbled in computational linguistics.
We are looking for high-aptitude adaptive thinkers who are willing to jump in and solve new problems using a variety of technical and non-technical approaches.
***Be aware of recruitment scams impersonating Hippocratic AI. All recruiting communication will come from @hippocraticai.com email addresses. We will never request payment or sensitive personal information during the hiring process. If anything appears suspicious, stop engaging immediately and report the incident.
How to Apply
Please apply through the job application page by clicking the 'Apply for this Job' button on the website.