{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreihtkngkqsam3t4xbpemdw7y7kdjnjnnbwcpm5dwv2ms776d626phu",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mi5mhmo3lzl2"
  },
  "path": "/t/hiring-lead-ai-ml-engineer-building-the-design-agent-multimodal-image-to-cad-stealth-startup/174736#post_1",
  "publishedAt": "2026-03-28T14:14:28.000Z",
  "site": "https://discuss.huggingface.co",
  "textContent": "**The Mission:**\n\nWe are building , a high-end AI Design Atelier that transforms creative human intent into production-ready jewelry. We aren’t just building another chatbot; we are building a multimodal pipeline that converts voice and text into 2D images to structured 3D geometry for manufacturing.\n\nWe are looking for a founding-level **AI/ML Engineer** to architect the bridge between **Gemini 1.5 Pro/2.5** and **Parametric 3D CAD engines**.\n\n**The Stack:**\n\n• **Foundation:** Gemini 1.5 Pro / Vertex AI (Multimodal focus).\n\n• **Infrastructure:** Python, FastAPI, Hugging Face Transformers.\n\n• **3D/Graphics:** Experience with Three.js, GLB/USDZ, or Rhino/Grasshopper API is a massive plus.\n\n• **Data:** RAG (Retrieval-Augmented Generation) for technical jewelry specs and material properties.\n\n**What You’ll Build:**\n\n• **The Vision Pipeline:** Fine-tuning multimodal prompts to ensure Gemini understands jewelry-specific spatial reasoning (prongs, shanks, stone settings).\n\n• **The Geometry Engine:** Converting Gemini’s JSON outputs into 3D meshes that meet real-world casting tolerances.\n\n• **The “Album” Logic:** Implementing an agentic memory system where the AI “remembers” a user’s aesthetic style across an entire collection.\n\n**Who You Are:**\n\n• You are bored with generic LLM wrappers and want to solve a **hard spatial problem**.\n\n• You have deep experience with **Structured Outputs (JSON)** and **Function Calling**.\n\n• You understand that in the luxury world, a 0.5mm error is the difference between a masterpiece and a failed cast.\n\n• You’ve shipped production-grade AI agents before.\n\n**Why Join Us?**\n\nWe are led by founders with deep domain expertise in the jewelry space. We have the industry DNA; we need your mathematical and architectural brain to make it “production-ready.”\n\n**Location:** Remote / Atlantic Canada (optional).\n\n**Compensation:** Open to discussion\n\n**How to Apply:** DM me here or send a link to your most impressive **Hugging Face Space** or **GitHub repo** that shows off your work with multimodal models.",
  "title": "Hiring Lead AI/ML Engineer | Building the design agent (Multimodal Image-to-CAD) | Stealth Startup"
}