Applied AI Engineer
About the team
Our team brings expertise from top institutions and frontier labs, including Google DeepMind, Meta FAIR, MIT, and AWS, alongside the business experience of founders who have built and exited companies.
We’re building a platform for deploying and improving AI agents in enterprises. We’re looking for a hands-on engineer to own the build alongside us.
About the role
You’ll work across agent harnesses, skills, tools, evaluations, and backend services. You’ll help decide how these pieces fit together, build them, and improve them through real use and feedback from our partners.
Architecture matters to us: how the system fits together, where complexity belongs, and how it evolves as we learn.
The platform is early, and some requirements will emerge as we build. You should enjoy investigating unfamiliar problems, making practical technical decisions, and taking work from an initial idea through to a working system.
What you’ll do
- Build the platform’s services, APIs, data models, and integrations.
- Develop agent harnesses, reusable skills, and reliable tools.
- Design how agents receive context, manage state, and coordinate work.
- Build evaluations that tell us whether the system is getting better.
- Turn failures and partner feedback into improvements.
- Own what you build through deployment, monitoring, and iteration.
Who you are
- You’re a strong software engineer who has shipped and maintained production systems.
- You’ve built with agents and understand how context, tools, and runtime decisions shape their behavior.
- You think carefully about architecture and where complexity should live.
- You use evaluations and traces to understand failures and improve systems.
- You’re comfortable with Python and backend development. Pydantic AI or similar experience is useful.
- You take ownership, communicate clearly, and change your mind when the evidence points elsewhere.