Research Resident

San Francisco•Residency•Undisclosed

Join us in pushing the boundaries of what's possible with LLMs and browser-native AI. You'll work on cutting-edge problems in agent systems (memory, search, personalization), context handling, tool use, and evals, while collaborating directly with our engineering team to bring novel approaches to production.

Perks

Mentorship: Access to leading researchers and mentors from top-tier academic and frontier research labs.
Hacker House: Live and work in our central SF 3-story loft.
Impact: Work directly with founders to shape the product.

What You'll Build

Research papers, blog posts, and public artifacts aimed at top-tier venues (NeurIPS, ICLR, ACL, CHI).
Design and experiment with novel LLM architectures, memory mechanisms, or tool-use strategies.
Develop evaluation frameworks for agent capabilities across diverse browser tasks.

Requirements

Demonstrated research experience in LLMs, applied mathematics, and/or theoretical computer science.
Strong programming skills in Python and TypeScript.
A track record of AI/ML/NLP publications in top conferences or journals, or evidence of rigorous, independent research (awards, fellowships, or open-source contributions highly valued).

Sample Projects

Develop benchmark suites to evaluate workflow agents that integrate browser interaction with tool-calling capabilities.
Build efficient indexing and retrieval systems for websites, applications, and workflow memory.
Innovate methods for dynamic knowledge graph creation and updating for personalized user experiences.
Design generative user interfaces that push the boundaries of human-computer interaction.