Job Title: Agent Architect, AI Healthcare Systems

Location: Palo Alto, CA (Onsite, 5 days a week)

Team: Engineering & Research

Partner: A pioneering company building the first safety-focused Large Language Model for healthcare.

About Our Hiring Partner

Our hiring partner is undertaking a monumental mission: to develop the first safety-focused Large Language Model designed specifically to transform global healthcare. Their goal is to dramatically improve health accessibility and outcomes by embedding deep medical expertise into an AI platform accessible to all. This represents a frontier of technology with the potential for unprecedented positive impact on human health.

The company was co-founded by a visionary group including CEO Munjal Shah, alongside leading physicians, hospital administrators, and AI researchers from world-renowned institutions such as Stanford, Johns Hopkins, and tech giants like Google and NVIDIA. With a substantial $278 million in funding from top-tier investors like Andreessen Horowitz and General Catalyst, they are equipped with the capital, network, and expertise to succeed. For professionals seeking impactful startup jobs in SFC, this is a chance to work on foundational technology with a elite team.

Why This Role is a Landmark Opportunity

1. Define a New Category: You won't be maintaining existing systems; you will be architecting the very paradigms for how intelligent, safe AI agents operate in healthcare.
2. Unrivaled Mission & Impact: Your work will directly contribute to AI systems that improve patient care and clinical outcomes on a global scale.
3. Learn from the Best: Collaborate with and learn from a world-class, cross-functional team of AI researchers, engineers, and healthcare professionals.
4. Resources to Innovate: As a well-capitalized, high-growth company, they provide the stability and resources needed for ambitious R&D, a key advantage for startup jobs in SFC.

About the Role

We are seeking an Agent Architect to design, develop, and pioneer the next generation of agentic systems that form the core of our healthcare-focused AI platform. This individual will act as a central architect, defining how our AI agents think, reason, and interact across a diverse range of critical clinical scenarios.

This role involves selecting the optimal agentic paradigms—from tool use and retrieval-augmented generation (RAG) to prompt engineering and model training—and establishing the underlying architecture for creating intelligent, safe, and responsive agents. You will work at the intersection of LLM system design, product innovation, and applied AI research, integrating cutting-edge techniques to continuously push the boundaries of what our agents can achieve.

Key Responsibilities

1. Architect and design novel AI agents tailored to a wide spectrum of clinical and operational healthcare use cases.
2. Evaluate and select the most effective agentic paradigm for each scenario (e.g., tool use, RAG, advanced prompting, model fine-tuning).
3. Choose the optimal models from our internal model library to power specific agent tasks and capabilities.
4. Collaborate closely with the research team to fine-tune models and systematically optimize agent behavior and performance.
5. Define and iterate on rigorous evaluation protocols in partnership with our dedicated evaluation team.
6. Pioneer new agent patterns and workflows to enable novel, safe, and effective capabilities.
7. Rapidly prototype and incorporate state-of-the-art techniques from scientific literature and the open-source community.
8. Track and integrate capabilities from emerging foundational models to enhance overall system performance and scope.

Required Qualifications

1. 5+ years of professional experience in a technical field such as software engineering, machine learning, data science, or AI product development.
2. Deep, practical understanding of agentic system design and the nuanced behaviors of large language models.
3. Proficiency with Python and modern machine learning toolkits and frameworks.
4. Hands-on experience building and evaluating non-deterministic AI/ML systems.
5. Strong analytical and problem-solving skills, complemented by a rigorous, experimental mindset.
6. Familiarity with core LLM paradigms such as prompting, RAG, fine-tuning, and tool/API integration.

Preferred Skills & Background

1. Experience designing agentic workflows or orchestration frameworks for LLMs.
2. A background in AI research or exposure to cutting-edge developments in NLP and machine learning.
3. Ability to translate complex technical concepts into robust, scalable system architectures.
4. A strong interest in healthcare applications, patient interaction design, and building safety-critical systems.
5. Excellent written and verbal communication skills, with a knack for clearly documenting design decisions and evaluation results.

A Note on Candidate Background

We recognize that Agent Architecture is a novel and rapidly evolving discipline. Ideal candidates may come from diverse backgrounds such as applied ML engineering, AI product design, prompt engineering, or NLP-focused research. If you are passionate about designing intelligent systems from the ground up and are driven to shape how LLMs interact with the world in a safe and impactful way, we strongly encourage you to apply.

This is a full-time, onsite role based in Palo Alto, CA. The company fosters a culture of in-person collaboration to accelerate innovation and build a strong, unified team.

Apply Now

If you are a technical pioneer eager to architect the future of AI in healthcare, we encourage you to apply. This role is a premier opportunity among startup jobs in SFC for those looking to define the next wave of intelligent systems.