Engineer in Residence: Slidelang

What You'll Build

• A prompt and structured-brief intake flow that produces a deck outline and spec.
• A deck compiler that turns the spec into multi-slide output with data-bound chart, math, and AI-generated image primitives.
• A browser editor for reviewing and editing generated slides, backed by validation and repair checks for layout, text, connectors, charts, math, and images.
• A presenter, publish, and share flow, plus a thin-client CLI or Codex plugin that lets agents create and validate decks through the hosted API.

What You'll Do

• Build the end-to-end hosted authoring app: AI-assisted deck planning, the deck compiler, the browser editor state model, the validation and repair pipeline, and the presenter/publish flow behind a hosted API.
• Partner with AI Fund internal teams and 2 to 3 external deck-heavy teams to define pilot scope, success metrics (time-to-first-draft, percent of slides accepted after light edits, layout QA pass rate, publish/share completion), data path, and the MVP cut line.
• Design the ladder from prompt-assisted drafting to agent-driven deck creation through the CLI or plugin, keeping every generated deck editable, inspectable, and reviewable rather than a static artifact.
• Make decisions about latency, layout validation, repair rules, and rendering reliability so generated decks are trustworthy enough to present and publish.
• Work with AI Fund's build team on product wedge, technical risk, and the path from pilot to a broader deck-authoring platform.

What You'll Need

• Strong backend and full-stack engineering: shipped production systems involving compilation, rendering, or document processing, with comfort in compilers, parsers, DSLs, or document-as-code, plus React or browser-editor experience.
• Demonstrated experience building GenAI products with retrieval, tool use, guardrails, and production feedback loops, including AI-assisted authoring or generation workflows.
• Product judgment for human-in-the-loop automation where the right answer is usually to remove busywork rather than replace the human outright.
• Ability to iterate with early users and translate ambiguous feedback into working product decisions.
• You actively use AI coding assistants and modern GenAI tools as part of your build workflow.
• US work authorization.

Helpful but Not Required

• Experience with presentation tools, Figma or design tooling, or visual layout engines.
• Background in data visualization, chart rendering, or image generation pipelines.
• Experience with CLI or plugin developer tools, marketplace or plugin packaging, collaborative document editing, or publishing workflows.
• Founder or founding engineer experience shipping a 0-to-1 product.