Hippocratic AI is looking to solve the problem of improving healthcare accessibility and health outcomes globally by developing a safety-focused Large Language Model (LLM) for healthcare, specifically focusing on voice-based generative AI in healthcare and clinically safe healthcare agents.
Requirements
- Strong programming skills in Python with experience in distributed systems, APIs, and data pipelines.
- Deep understanding of prompt engineering, vector databases, and retrieval systems (RAG), voice agents or willingness to learn rapidly.
- Experience with cloud environments (AWS/GCP/Azure) and modern DevOps practices (Terraform, CI/CD, monitoring).
- Experience building and shipping AI- or ML-powered products in production environments.
- Experience building or deploying LLM-based or multi-agent systems at scale.
- Hands-on work with speech recognition, text-to-speech, or streaming architectures for real-time AI experiences.
Responsibilities
- Design, build, and optimize production-grade AI pipelines that power our voice-based generative healthcare agents—from retrieval-augmented generation (RAG) to multi-step reasoning systems.
- Prototype and deploy zero-to-one features using state-of-the-art LLMs, retrieval systems, and streaming architectures—balancing innovation with reliability.
- Develop and refine AI-native workflows that support real-time, conversational, and long-running interactions across diverse healthcare contexts.
- Drive continuous improvement in model evaluation, safety testing, and observability, ensuring every agent interaction meets clinical safety standards.
- Design and build the intelligent systems that power our clinically safe healthcare agents, working at the intersection of large language models, real-time voice, and human-centered product design.
- Build scalable RAG and multi-agent pipelines to conversational interactions.
Other
- 3+ years of professional experience in software, ML, or AI engineering.
- Collaborate cross-functionally with product, clinical, and engineering teams to translate healthcare workflows into safe, scalable, and human-centered AI experiences.
- Excellent communication, cross-functional collaboration, and an ability to move fast in high-impact domains.
- Prior exposure to healthcare, safety-critical domains, or regulated product development.
- 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.
