<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Eugen Miknevic</title><link>https://eugenmik.github.io/</link><description>Recent content on Eugen Miknevic</description><image><title>Eugen Miknevic</title><url>https://eugenmik.github.io/images/og-default.jpg</url><link>https://eugenmik.github.io/images/og-default.jpg</link></image><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 09 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://eugenmik.github.io/index.xml" rel="self" type="application/rss+xml"/><item><title>FoundryFlash: GPU casting simulator</title><link>https://eugenmik.github.io/projects/foundryflash/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://eugenmik.github.io/projects/foundryflash/</guid><description>A casting solidification simulator that runs in the browser, from STEP upload to a feeding decision, with a Julia and CUDA solver behind it.</description></item><item><title>castsolid-gnn: solidification surrogate</title><link>https://eugenmik.github.io/projects/castsolid-gnn/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://eugenmik.github.io/projects/castsolid-gnn/</guid><description>A graph neural network that predicts where a casting solidifies last, in seconds instead of hours. Weights published on Hugging Face under Apache-2.0.</description></item><item><title>GussCore: AI-assisted foundry ERP/MES</title><link>https://eugenmik.github.io/projects/gusscore/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://eugenmik.github.io/projects/gusscore/</guid><description>Production management for iron and steel foundries. Workers report by voice or photo, and a person confirms every AI proposal.</description></item><item><title>techbookocr: scanned technical books to Markdown</title><link>https://eugenmik.github.io/projects/techbookocr/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://eugenmik.github.io/projects/techbookocr/</guid><description>Local OCR that turns old scanned metallurgy and foundry handbooks into Markdown with tables, formulas and figures, for a knowledge base in Obsidian.</description></item><item><title>AlloyForge: superalloy design assistant</title><link>https://eugenmik.github.io/projects/alloyforge/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://eugenmik.github.io/projects/alloyforge/</guid><description>A tool for screening heat-resistant nickel, cobalt and iron superalloys, with a search over metallurgy literature.</description></item><item><title>Foundry Interview Prep: practice from a resume</title><link>https://eugenmik.github.io/projects/foundry-interview-prep/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://eugenmik.github.io/projects/foundry-interview-prep/</guid><description>A Streamlit app that reads a resume and runs a mock foundry interview, with a language model scoring the answers. Built as a course project.</description></item><item><title>Publishing a casting model: what it took to make the weights runnable</title><link>https://eugenmik.github.io/posts/publishing-a-casting-model/</link><pubDate>Fri, 09 Oct 2026 00:00:00 +0000</pubDate><guid>https://eugenmik.github.io/posts/publishing-a-casting-model/</guid><description>Releasing the solidification surrogate was not a matter of uploading a checkpoint. Checking that the published files reproduce the internal ones, and reporting the results honestly, took longer than the upload.</description></item><item><title>Human-in-the-loop AI on the foundry floor</title><link>https://eugenmik.github.io/posts/human-in-the-loop-ai-foundry-floor/</link><pubDate>Tue, 06 Oct 2026 00:00:00 +0000</pubDate><guid>https://eugenmik.github.io/posts/human-in-the-loop-ai-foundry-floor/</guid><description>Five design rules from building GussCore, a foundry ERP/MES where workers report by voice and a person confirms every AI proposal.</description></item><item><title>Validating a GPU solidification solver: from +51% to within 3.7%</title><link>https://eugenmik.github.io/posts/validating-gpu-solidification-solver/</link><pubDate>Tue, 06 Oct 2026 00:00:00 +0000</pubDate><guid>https://eugenmik.github.io/posts/validating-gpu-solidification-solver/</guid><description>How I checked the FoundryFlash solver, and how the largest error turned out to be in the sand data.</description></item><item><title>Voxels or tetrahedra: what casting AI needs from the mesh</title><link>https://eugenmik.github.io/posts/voxels-or-tetrahedra/</link><pubDate>Tue, 06 Oct 2026 00:00:00 +0000</pubDate><guid>https://eugenmik.github.io/posts/voxels-or-tetrahedra/</guid><description>A staircase boundary misstates the cooling rate where feeding decisions are made. What my own voxel prototype measured, and why a tetrahedral mesh suits a neural network.</description></item><item><title>About</title><link>https://eugenmik.github.io/about/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://eugenmik.github.io/about/</guid><description>&lt;p&gt;I am a foundry engineer. Since 2006 I have designed casting technology, run casting simulations and brought new foundries into production. Over my career I have developed about 1,000 casting technologies.&lt;/p&gt;
&lt;p&gt;I did not retrain as an AI engineer. I learned modern AI, from graph neural networks to language models, so that I could combine it with what I know about casting. I use it to build software tools for foundries and metallurgy: a GPU solidification solver, a neural network that predicts hot spots from a STEP file in seconds, and shop-floor software where workers report by voice and a person stays in control of what gets saved.&lt;/p&gt;</description></item><item><title>Legal &amp; Privacy</title><link>https://eugenmik.github.io/legal/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://eugenmik.github.io/legal/</guid><description>&lt;h2 id="contact"&gt;Contact&lt;/h2&gt;
&lt;p&gt;Eugen Miknevic&lt;br&gt;
Senftenberg, Germany&lt;br&gt;
Email: &lt;a href="mailto:eugenmiknevic@gmail.com"&gt;eugenmiknevic@gmail.com&lt;/a&gt;&lt;/p&gt;
&lt;p&gt;This is a private, non-commercial website. It presents information about my professional background, my projects and my articles. Nothing is sold or offered here.&lt;/p&gt;
&lt;h2 id="privacy"&gt;Privacy&lt;/h2&gt;
&lt;ul&gt;
&lt;li&gt;The site is hosted on GitHub Pages, operated by GitHub, Inc. When you open a page, GitHub's servers process technical data such as your IP address to deliver it. GitHub may process this data on servers in the United States. This is described in the &lt;a href="https://docs.github.com/en/site-policy/privacy-policies/github-general-privacy-statement"&gt;GitHub General Privacy Statement&lt;/a&gt;.&lt;/li&gt;
&lt;li&gt;I use no cookies, no analytics, no tracking and no third-party embeds. Fonts and scripts are served from this site.&lt;/li&gt;
&lt;li&gt;If you email me, I use your message only to reply.&lt;/li&gt;
&lt;/ul&gt;
&lt;p&gt;Links to external websites lead to content for which their operators are responsible.&lt;/p&gt;</description></item></channel></rss>