/tags/meta/Recent content in Meta onHugoenMon, 29 Jun 2026 00:00:00 +0000/projects/research-engineer-trajectory/Mon, 29 Jun 2026 00:00:00 +0000/projects/research-engineer-trajectory/<p>A 6-month personal study direction. I am becoming someone who understands modern LLMs across abstraction levels — from math to metal — with a focus on transformers, inference systems, and efficient kernels.</p> <p><a href="/research-engineer-trajectory-2026-06/">Read the full living note</a></p>/research-engineer-trajectory-2026-06/Mon, 29 Jun 2026 00:00:00 +0000/research-engineer-trajectory-2026-06/<blockquote> <p>Status: direction, not a plan<br> Horizon: ~6 months, with weekly check-ins against this note</p></blockquote> <hr> <h2 class="heading" id="what-this-is"> What this is <a href="#what-this-is">#</a> </h2> <p>A reference document capturing a long conversation about how to spend the next ~6 months of personal study time. It is a living note, not a fixed plan. It will be revised as the work reveals what actually matters.</p> <hr> <h2 class="heading" id="starting-identity"> Starting identity <a href="#starting-identity">#</a> </h2> <p>I am becoming someone who understands modern LLMs and transformers across abstraction levels — from the math to the metal. The working title is <strong>research engineer with inference engineer capabilities</strong>, but the exact craft will emerge from the work. The trunk is transformers and inference. Branches may form later.</p>/weekly/2026-w26/Mon, 29 Jun 2026 00:00:00 +0000/weekly/2026-w26/<p>June 29 — July 5, 2026</p> <h2 class="heading" id="this-week"> This week <a href="#this-week">#</a> </h2> <ul> <li>Revived this site as a public record of a 6-month research engineering trajectory.</li> <li>Settled on a structure: transformers + LLM inference + efficient kernels as the core trunk; agents, SOTA papers, and TypeScript literacy as satellites.</li> <li>Blocked study time on the calendar for the next 8 weeks.</li> <li>Started a living note to track direction: <a href="/projects/research-engineer-trajectory/">Research Engineer Trajectory</a>.</li> </ul> <h2 class="heading" id="up-next"> Up next <a href="#up-next">#</a> </h2> <ul> <li>Read the Word2Vec paper and understand CBOW / skip-gram / negative sampling.</li> <li>Implement Word2Vec from scratch in NumPy or raw PyTorch.</li> <li>Explore <a href="https://github.com/huggingface/tau">Tau</a> as a Python agent harness for MVF work.</li> </ul> <h2 class="heading" id="open-questions"> Open questions <a href="#open-questions">#</a> </h2> <ul> <li>What part of the transformer/inference stack lights me up most as I go deeper?</li> <li>How much focused work can I realistically get from the 3–7pm weekday blocks?</li> </ul>/posts/my-first-post/Sun, 02 Feb 2025 00:00:00 +0000/posts/my-first-post/<p>This site is being revived as a public record of my work and learning.</p> <p>Expect:</p> <ul> <li><strong>Weekly notes</strong> — what I studied, built, and got wrong.</li> <li><strong>Posts</strong> — deeper writeups on transformers, inference, and systems.</li> <li><strong>Projects</strong> — code, experiments, and reproductions.</li> </ul> <p>Current focus: understanding large language models from the math to the metal.</p>