About the Role
We are looking for an AI engineer to build the LLM-powered systems at the core of our product. You will own the agentic systems that carry multi-step work from start to finish, the evaluation infrastructure, the retrieval layer, and the AI features our internal users rely on. You'll work directly with the founders and have significant room to shape what gets built.
Responsibilities
- Build agents that do real work, designing and shipping LLM-powered systems that see multi-step tasks through.
- Own quality and evaluation by building infrastructure to measure AI performance and improve prompts, retrieval, and models.
- Build the knowledge layer by designing retrieval systems and ensuring knowledge accuracy, versioning, and freshness.
- Build AI into the product by shipping copilots and assistive features to increase user speed.
- Close the loop on real usage by deploying to production, monitoring systems, and improving based on user interaction.
- Shape the technical roadmap by working with founders on future builds and making informed bets on AI technology.
- Lay the foundation for scale by making architectural decisions and building with future engineers in mind.
Requirements
- Experience building and shipping LLM-powered systems or agents to production that handle real user usage.
- Strong overall AI fluency, including reasoning about prompting, tool use, context management, retrieval, latency, cost, and failure modes.
- Experience building evaluation into work, designing metrics, capturing production signal, and systematically improving quality.
- Experience monitoring and debugging AI systems in production and ensuring their reliability.
- Solid software engineering fundamentals, including writing maintainable code and owning shipped products.
- Comfort with ambiguity and a desire to build the playbook.
- Proactive, analytically sharp, high standards with attention to detail, passionate, and open.
Skills
- LLM-powered systems
- Agentic systems
- Evaluation infrastructure
- Retrieval systems
- AI features
- Prompting
- Tool use
- Context management
- Latency
- Cost management
- Failure mode analysis
- Metrics design
- Production signal capture
- System monitoring
- Debugging
- Software engineering fundamentals
- Python
- TypeScript
- FastAPI
- Next.js
- Postgres
Location
- Remote
Work Type
- Full-time
Experience Level
- Early-stage company experience
- Senior
Salary/Compensations
- Competitive compensation
- Meaningful early equity
Benefits
- Meaningful early equity
About the Company
- Mira Mace pairs Medicare beneficiaries with a dedicated healthcare advocate who navigates appointments, insurance, and care coordination.
- Our customers receive support from nurses while AI handles backend work, all covered by Medicare.
- We aim to provide affordable, personalized health assistance to everyone, navigating the healthcare system and promoting health.
- The founding team has technical experience from Google, Meta, Dropbox, and Amazon, along with startup experience.
- We are backed by Foundation Capital, DefineVC, and top Silicon Valley angel investors.
