About the role
About Novoflow
Novoflow is building AI Employees for medical clinics. We see two industry-breaking problems: over 400 EHRs, 1000s of vendors, and millions of patients all lacking interoperability across healthcare, and a trail of operational inefficiency following it. We’re building the scalable, reliable, and safe AI infrastructure that solves this problem.
With multi-year contracts secured and strong investor backing from YC advisors and top investors, we’re scaling our engineering fast to meet skyrocketing demand.
Why Join Us?
- Impact: Be a key contributor to cutting-edge projects, transforming industries.
- Growth: Thrive in a dynamic, high-ownership environment alongside top-tier talent.
- Innovation: Work with advanced tools and push technological boundaries.
- Autonomy: Drive your own initiatives and influence the company’s technical direction.
About the Role
We’re seeking an LLM engineer with hands-on experience in architecting strong prompting for agents. This role isn’t as much of a customer-by-customer prompt tuning, but rather building scalable AI infrastructure for our computer agents through context, prompting, and adjacent backend engineering. If you thrive in a fast-paced, high-ownership environment, we want to hear from you.
What You’ll Do:
- Design custom prompt frameworks for our various core infrastructure agents.
- Build smart context engineering. This will be a mix between backend work and smart system design.
- Realistically, anything that touches an LLM is in your realm of design. How can we tackle safety, reliability, and latency at scale..
- Technical Leadership: Drive technical decisions and architecture design, shaping the foundation of our solutions.
