Engineering
Remote (Global)
AI Engineer
Help us build AI agents that can complete real tasks. You'll work on improving reliability, adding new capabilities, and shipping features.
About the role
We're building AI agents that can take on real work, not just answer questions. The goal is to create something people can rely on to complete tasks from start to finish.
In this role, you'll spend most of your time improving our agents. That includes writing better prompts, building evaluation systems, debugging failures, and trying new approaches when current ones hit limits.
We're a small, remote team. You'll have significant ownership over your work and direct impact on the product.
What you'll do
- Build and maintain AI agents that handle real tasks end-to-end
- Work on prompt engineering, context management, and tool integrations
- Develop evaluation systems to track agent performance
- Debug agent failures and improve reliability
- Ship features alongside the product and design team
- Stay current with new models and techniques
What we're looking for
- Experience building LLM-powered products or agents
- Solid understanding of prompting techniques and agent patterns
- Proficient in Python
- Experience shipping AI agents to production
- Comfortable debugging unpredictable AI behavior
Bonus points
- Experience with multi-agent systems or complex tool use
- Background in reinforcement learning or planning
- Open source contributions in AI
- Published writing or research on AI topics
Interested?
Send us your resume and a short note about yourself. Include any relevant projects or work.