About the roleYou'll build the AI systems that power taste agent harnesses, memory, evals, tooling, data collection, index, search, graph, crawling, scraping, security and more.
Types of problems you'd work on- Craft agent harnesses, memory and self-improvement loops
- Design evaluation pipelines and synthetic data generation
- Create embedding and retrieval infrastructure that scales to millions of requests
- Build crawling and scraping systems for visual data across the web
- Set up inference serving and APIs for client-facing products
- Manage security sweeps vulnerability mapping
- Develop the tooling and infrastructure that makes everything reliable and fast
What matters to us- Deeply technical: you're deeply opinionated about what good code means, you have an AI-forward setup while being anti-slop, you care deeply about the craft.
- You're creative and have genuine curiosity about 'taste' and making subjective domains verifiable
- You have startup DNA: you move fast, adapt, no such thing as 'not in scope', you like ambiguous, hard problems
- AI experience: you need experience building AI forward products, systems, agents, models and more.
- You care about arriving at the simple, clear solution vs. the complex one
Bonus points- Open source contributions or personal projects that show you build things because you're curious
- Background at creative companies (Figma, Notion, Canva, Adobe, Runway, etc.) or companies with strong index building/crawling (e.g. Firecrawl, Brave, Luma, Pika) or data (Mercor, Surge, etc.)
