ABOUT US:

Hippocratic AI is building safety-focused large language model (LLM) for the healthcare industry. Our team comprised of ex-researchers from Microsoft, Meta, Nvidia, Apple, Stanford, John Hopkins and HuggingFace are reinventing the next generation of foundation model training and alignment to create AI-powered conversational agents for real time patient-AI interactions.

REQUIRED QUALIFICATIONS:

• 5+ years in a technical field such as software engineering, machine learning, data science, or AI product development
• Deep understanding of agentic system design and language model behaviors
• Proficiency with Python and modern ML tooling
• Experience building and evaluating non-deterministic AI/ML systems
• Strong analytical and problem-solving skills, with an experimental mindset
• Familiarity with LLM paradigms such as prompting, RAG, fine-tuning, and tool use

PREFERRED SKILLS:

• Experience designing agentic workflows or orchestration frameworks for LLMs
• Background in AI research or exposure to cutting-edge developments in NLP
• Ability to translate complex technical ideas into scalable architectures
• Interest in healthcare applications, patient interaction design, and safety-critical systems
• Excellent written and verbal communication skills, with the ability to clearly document design decisions and evaluations

WHY JOIN OUR TEAM:

• Innovative Mission: We are developing a safe, healthcare-focused large language model (LLM) designed to revolutionize health outcomes on a global scale.
• Visionary Leadership: Hippocratic AI was co-founded by CEO Munjal Shah, alongside a group of physicians, hospital administrators, healthcare professionals, and artificial intelligence researchers from leading institutions, including El Camino Health, Johns Hopkins, Stanford, Microsoft, Google, 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.
• World-Class Team: Our team is composed of leading experts in healthcare and artificial intelligence, ensuring our technology is safe, effective, and capable of delivering meaningful improvements to healthcare delivery and outcomes.
  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 Agent Architect to design, develop, and innovate the next generation of agentic systems that drive our healthcare-focused AI platform. This individual will serve as a central architect in shaping how our agents think, act, and interact across diverse clinical use cases.
You will be responsible for selecting the right agentic paradigms—ranging from tool use, retrieval-augmented generation (RAG), and prompt engineering, to model training—and defining the underlying architecture for intelligent, safe, and responsive agents. You will work closely with our research, engineering, and evaluation teams to integrate cutting-edge techniques and continuously push the boundaries of agent capabilities.
This role blends deep technical knowledge with strategic thinking and experimentation. It’s ideal for those who thrive at the intersection of LLM system design, product innovation, and applied AI research.

RESPONSIBILITIES:

• Architect and design new AI agents across a variety of clinical and operational use cases
• Evaluate and select the optimal agentic paradigm for each scenario (e.g., tools, engines, prompting, RAG, model training)
• Choose the appropriate models from our internal model library for specific tasks
• Collaborate with the research team to fine-tune models and optimize agent behavior
• Define and iterate on evaluation protocols in partnership with the evaluation team
• Develop new agent patterns and workflows to enable novel capabilities and interactions
• Rapidly incorporate state-of-the-art techniques from the latest scientific literature and open-source developments
• Track and integrate capabilities from emerging foundational models to improve system performance and scope