--- title: Elon Musk chose Vera Rubin for orbit. Now it must be... description: SpaceX and Nvidia announced plans to adapt Nvidia's Vera Rubin NVL72 rack-scale AI platform for orbital deployment aboard SpaceXAI's Starmind satellites, with... canonical: https://daily.dev/posts/elon-musk-chose-vera-rubin-for-orbit-now-it-must-be-redesigned-for-space--orzietvnw twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Elon Musk chose Vera Rubin for orbit. Now it must be redesigned for space. | daily.dev og:description: SpaceX and Nvidia announced plans to adapt Nvidia's Vera Rubin NVL72 rack-scale AI platform for orbital deployment aboard SpaceXAI's Starmind satellites, with... og:url: https://daily.dev/posts/elon-musk-chose-vera-rubin-for-orbit-now-it-must-be-redesigned-for-space--orzietvnw og:image: https://api.daily.dev/og/posts/ORZIetvnW.png og:image:alt: Elon Musk chose Vera Rubin for orbit. Now it must be redesigned for space. og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Elon Musk chose Vera Rubin for orbit. Now it must be redesigned for space. **[The New Stack](https://daily.dev/sources/newstack)** · 5 min read · 0 upvotes · 0 comments ## Summary SpaceX and Nvidia announced plans to adapt Nvidia's Vera Rubin NVL72 rack-scale AI platform for orbital deployment aboard SpaceXAI's Starmind satellites, with a first launch targeted for Q4 2027 and larger scale by 2028. Elon Musk framed the move as part of SpaceX building exclusively on Nvidia's Vera Rubin architecture going forward, on Earth and in orbit. Experts note major engineering hurdles remain: space lacks convective cooling, so heat must be radiated via deployable radiators, and LEO radiation levels (100-1,000 rad(Si)/year) would degrade commercial-off-the-shelf electronics over a multiyear mission. A realistic near-term system would likely be radiation-tolerant and fault-managed rather than fully radiation-hardened, relying on shielding, ECC, redundancy, and reduced-performance fallback modes rather than a ground-up hardened redesign. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What AI chip architecture is SpaceX using for its Starmind orbital AI satellites? SpaceX and Nvidia are basing SpaceXAI's Starmind satellite computing core on a space-optimized version of Nvidia's Vera Rubin NVL72 rack-scale AI platform, which on Earth combines 72 Rubin GPUs and 36 Vera CPUs with ConnectX-9 SuperNICs. SpaceX targets a first orbital launch in Q4 2027, with significant scale planned for 2028. _Following how AI hardware architectures evolve from data centers into new environments is easier with daily.dev._ ### How much radiation does electronics in low Earth orbit have to withstand per year? NASA cites typical trapped-particle dose rates of 100 to 1,000 rad(Si) per year for low-inclination LEO spacecraft below 500 km. This level does not immediately destroy electronics but causes cumulative degradation over a multiyear mission, which is why commercial off-the-shelf chips like Nvidia's GPUs would need shielding, ECC, redundancy, and fault-tolerant design to survive long-term orbital deployment. _Engineers evaluating radiation-hardened versus commercial hardware for space workloads can track this on daily.dev._ ### Why can't a standard Nvidia NVL72 AI rack be cooled in space the same way it is on the ground? A conventional NVL72 rack assumes gravity, technicians, stable grid power, a building-scale liquid loop, and frequent part replacement, all of which orbit removes. Vacuum does not carry heat away through convection, so heat must travel from chips to radiator surfaces and leave as infrared radiation, requiring closed-loop liquid cooling and large deployable radiators instead of chillers, cooling towers, and fans. _Anyone weighing novel cooling approaches for high-density AI hardware can follow this design challenge on daily.dev._ ## Similar posts on daily.dev - [Nvidia rolls out Rubin Module for space-based computing](https://daily.dev/posts/nvidia-rolls-out-rubin-module-for-space-based-computing-5qti91gu3) · The Register · 1 upvotes · 0 comments --- Tags: [#nvidia](https://daily.dev/tags/nvidia), [#gpu](https://daily.dev/tags/gpu), [#spacex](https://daily.dev/tags/spacex), [#ai-infrastructure](https://daily.dev/tags/ai-infrastructure) [View this post on daily.dev](https://daily.dev/posts/elon-musk-chose-vera-rubin-for-orbit-now-it-must-be-redesigned-for-space--orzietvnw) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Elon Musk chose Vera Rubin for orbit. Now it must be redesigned for space.","url":"https://daily.dev/posts/elon-musk-chose-vera-rubin-for-orbit-now-it-must-be-redesigned-for-space--orzietvnw","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/elon-musk-chose-vera-rubin-for-orbit-now-it-must-be-redesigned-for-space--orzietvnw"},"datePublished":"2026-08-31T19:01:20.401Z","dateModified":"2026-08-31T19:22:34.770Z","description":"SpaceX and Nvidia announced plans to adapt Nvidia's Vera Rubin NVL72 rack-scale AI platform for orbital deployment aboard SpaceXAI's Starmind satellites, with...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/1008b6de4cd20dc9b950b907d2de7b45?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/1008b6de4cd20dc9b950b907d2de7b45?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The New Stack","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"The New Stack","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/newstack","url":"https://daily.dev/sources/newstack"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/elon-musk-chose-vera-rubin-for-orbit-now-it-must-be-redesigned-for-space--orzietvnw","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"nvidia,gpu,spacex,ai-infrastructure","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The New Stack","item":"https://daily.dev/sources/newstack"},{"@type":"ListItem","position":3,"name":"Elon Musk chose Vera Rubin for orbit. Now it must be redesigned for space."}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/elon-musk-chose-vera-rubin-for-orbit-now-it-must-be-redesigned-for-space--orzietvnw#faq","mainEntity":[{"@type":"Question","name":"What AI chip architecture is SpaceX using for its Starmind orbital AI satellites?","acceptedAnswer":{"@type":"Answer","text":"SpaceX and Nvidia are basing SpaceXAI's Starmind satellite computing core on a space-optimized version of Nvidia's Vera Rubin NVL72 rack-scale AI platform, which on Earth combines 72 Rubin GPUs and 36 Vera CPUs with ConnectX-9 SuperNICs. SpaceX targets a first orbital launch in Q4 2027, with significant scale planned for 2028. Following how AI hardware architectures evolve from data centers into new environments is easier with daily.dev."}},{"@type":"Question","name":"How much radiation does electronics in low Earth orbit have to withstand per year?","acceptedAnswer":{"@type":"Answer","text":"NASA cites typical trapped-particle dose rates of 100 to 1,000 rad(Si) per year for low-inclination LEO spacecraft below 500 km. This level does not immediately destroy electronics but causes cumulative degradation over a multiyear mission, which is why commercial off-the-shelf chips like Nvidia's GPUs would need shielding, ECC, redundancy, and fault-tolerant design to survive long-term orbital deployment. Engineers evaluating radiation-hardened versus commercial hardware for space workloads can track this on daily.dev."}},{"@type":"Question","name":"Why can't a standard Nvidia NVL72 AI rack be cooled in space the same way it is on the ground?","acceptedAnswer":{"@type":"Answer","text":"A conventional NVL72 rack assumes gravity, technicians, stable grid power, a building-scale liquid loop, and frequent part replacement, all of which orbit removes. Vacuum does not carry heat away through convection, so heat must travel from chips to radiator surfaces and leave as infrared radiation, requiring closed-loop liquid cooling and large deployable radiators instead of chillers, cooling towers, and fans. Anyone weighing novel cooling approaches for high-density AI hardware can follow this design challenge on daily.dev."}}]} ```