2 months ago
Responsibilities
- Build and ship LLM-powered agents that complete multi-step work, interact with internal systems and third parties, and hand off to humans when appropriate.
- Own AI quality and evaluation infrastructure, including metrics, regression detection, production signal capture, and improvement of prompts, retrieval, and models.
- Design retrieval systems and maintain accurate, versioned, and fresh knowledge sources for agents.
- Build copilots and assistive AI features for internal users with appropriate model-versus-human judgment.
- Deploy AI systems to production, monitor real-world behavior, and improve them based on usage feedback.
- Shape the technical roadmap with the founders based on current model capabilities and limitations.
- Make architectural decisions that support significant growth and create a strong foundation for future engineers.
Requirements
- Experience building and shipping LLM-powered systems or agents to production for real users.
- Strong fluency in prompting, tool use, context management, retrieval, latency, cost, and AI system failure modes.
- Experience designing evaluation metrics, capturing production signals, and systematically improving AI quality.
- Experience monitoring and debugging AI systems in production and maintaining their reliability.
- Solid software engineering fundamentals and ability to write maintainable code and own shipped systems.
- Comfort working in an ambiguous early-stage environment.
- Preferred: depth in RAG, retrieval systems, vector databases, and maintaining fresh knowledge corpora.
- Preferred: experience with RLHF, reward modeling, or similar feedback-driven LLM improvement loops.
- Preferred: healthcare or regulated-industry experience, including HIPAA and PII/PHI handling.
- Preferred: Python and TypeScript experience.
Benefits
- Work directly with the founders.
- Meaningful early equity and competitive compensation.
- Wide scope across agents, evaluations, retrieval, copilots, and emerging AI use cases.
- Opportunity to shape the technical roadmap and foundational architecture at an early-stage healthcare company.
- Fast shipping and experimentation-focused environment.
Tech Stack
Categories
About Mira Mace
Mira Mace pairs Medicare beneficiaries with a dedicated healthcare advocate who navigates appointments, insurance, and care coordination on their behalf. Mira Mace customers get the support of caring nurses while AI agents do the tedious backend work, all covered by Medicare. Today a 24X7 personalized health assistance is only available to the rich or extremely sick. Our vision is for everyone to be able to afford a health assistant who knows your health history deeply, navigates the healthcare system on your behalf, and propels you to become the healthiest version of yourself. We are backed by Foundation Capital, DefineVC and top Silicon Valley angel investors.