Visiting Engineer: Research Coach

Responsibilities

• Own the user journey from early research question to draft refinement and evidence review.
• Design guardrails that enforce coaching behavior instead of drifting into ghostwriting.
• Build multi-step agentic workflows with strong traceability, citation grounding, and failure handling.
• Talk to students, parents, or educators to learn where the process helps versus harms.
• Work with AI Fund's build team on product positioning, pedagogy, and technical tradeoffs.

What you'll build

• A guided workflow for question refinement, source review, note-taking, drafting support, and rubric-aware feedback.
• Citation verification grounded in real scholarly sources rather than generic model claims.
• A transparent authorship log that distinguishes student-written work from AI scaffolding or suggestions.
• Optional sandboxed experimentation or code execution where computational work is part of the research process.

Requirements

• Strong full-stack engineering ability and real hands-on experience shipping multi-step GenAI systems.
• Experience with citation grounding, retrieval, agent orchestration, evals, or developer-tool style workflows.
• Product judgment around trust, educational integrity, and how much help a student should receive.
• A bias toward clear UX for complex workflows rather than impressive but brittle demos.
• You know how to use AI coding assistants and modern AI tools to increase speed without surrendering product judgment.
• US work authorization.

Nice-to-haves

• Edtech experience or a personal connection to research education.
• Experience building code sandboxes, notebook-style tools, or pedagogy-heavy products.
• Experience with LangGraph, Claude Agent SDK, or similar workflow tooling.

Compensation

• $10,000/month for 12 weeks ($30,000 total).
• This is a contract role during the residency. If the build leads to a funded company, the next step is a founder-level role with meaningful equity upside.