{"id":125553,"title":"ArchGen Labs | Building skyscrapers for semiconductor chips","tagline":"AI-powered chip design tools for the next generation of 3D semiconductors.","body":"**TLDR; We’re building the tools to out more transistors on a chip. Our foundational models run roughly 5,000× faster than current EDA software and our core placement engine ranked is #1 globally in Hudson River Trading’s macro-placement challenge.**\\\n\\\n<https://www.youtube.com/watch?v=39z8-MXMiOI>\n\nHey everyone! We’re[ Hariharan Ayappane](https://www.linkedin.com/in/hariharan-ayappane/) and[ Naveen Venkat](https://www.linkedin.com/in/naveenvenkat17/), the founders of[ ArchGen Labs (YC F26)](https://archgenlabs.com/).\n\n### **Chips of the future will be 3D**\n\nFor decades, better chips came from making transistors smaller. That’s getting harder and more expensive, while AI keeps demanding more compute within the same power and cooling budgets.\n\nPart of the problem is distance. Moving data between components takes time and energy. Stacking computation vertically, like floors in a skyscraper, can bring those components closer together.\n\nBut shorter connections come with a trade-off: more computation in the same space makes heat harder to remove.\n\nEngineers need to optimize placement, timing, and temperature together. Every change needs feedback. When those checks take too long, teams explore fewer designs.\n\nWe accelerate that loop.\n\n### **What we’re building**\n\n**1. Ultrafast foundational models for chip design**\n\nLayerTherm uses physics-informed neural networks to predict a chip’s temperature map from its power distribution.\n\nIn our benchmarks, predictions averaged **62 milliseconds versus 314 seconds** for EDA solvers - roughly **5,000× faster**.\n\nThat lets engineers screen more candidate designs for hotspots before detailed thermal verification.\n\n![uploaded image](/media/?type=post&id=125553&key=user_uploads/3342660/3312c464-8b5c-4a0e-8cb4-5a2f64dd0de4)\n\n**2. Worlds best chip design engine**\n\nOur GPU-accelerated tools help engineers decide which components belong on each layer, shorten critical connections, and evaluate timing and thermal trade-offs.\n\nThe core placement engine ranked #1 globally in Hudson River Trading’s macro-placement challenge:[ https://archgenlabs.com/blog/posts/how-we-ranked-first-in-the-partcl.html](https://archgenlabs.com/blog/posts/how-we-ranked-first-in-the-partcl.html)\n\n![uploaded image](/media/?type=post&id=125553&key=user_uploads/3342660/6e1de1c7-ae47-4834-a974-8c54ba0b3474)\n\n**3. Fully autonomous AI chip design engineer**\n\nNewton works through placement, routing, design-rule violations, and timing repairs. It tests candidate changes, rejects weak ones before expensive checks, and carries forward verified results.\n\n![uploaded image](/media/?type=post&id=125553&key=user_uploads/3342660/6fd919cb-a7fd-49a0-85be-dcce33a92b02)\n\n### **Where we are**\n\nWe’ve signed pilot projects and are working with GlobalFoundries to build 3D chips. We’re targeting our first tapeout in mid-2027.\n\n### **Our ask**\n\nWe’d love to meet:\n\n* Physical-design and timing teams facing a difficult closure problem or an upcoming tapeout.\n* AI accelerator and 3D IC teams working through power, interconnect, or thermal constraints.\n* Foundry and advanced-packaging engineers interested in evaluating tools for stacked logic.\n\nIf that sounds like your team, tell us where your design process gets stuck. We’d love to explore it with you.\n\nReach us at [founders@archgen.tech](mailto:founders@archgen.tech)\n\n🚀[ ](https://archgen.tech/)[archgenlabs.com](http://archgen.com)","slug":"Wf3-archgen-labs-building-skyscrapers-for-semiconductor-chips","created_at":"2026-11-09T17:00:59.345Z","updated_at":"2026-11-18T05:19:49.398Z","total_vote_count":9,"url":"https://www.ycombinator.com/launches/Wf3-archgen-labs-building-skyscrapers-for-semiconductor-chips","share_image_url":"//bookface-static.ycombinator.com/assets/ycdc/yc-og-image-c440a0ad1dacfb86eeeb343717479cc54d256614449b4ef719977a0a451f8bc8.png","company":{"id":36048,"name":"Archgen Labs","slug":"archgen-labs","url":"https://www.archgen.tech/","logo":"https://bookface-images.s3.amazonaws.com/small_logos/859bb4acfd797a8066a3332a29dbfc4ee42fcb0e.png","batch":"Fall 2026","industry":"Industrials","tags":["Hardware","Semiconductors","AI"],"search_path":"https://bookface.ycombinator.com/company/36048"}}