Cv on martinuke0's Blog https://martinuke0.github.io/tags/cv/ Recent content in Cv on martinuke0's Blog martinuke0's Blog https://martinuke0.github.io/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E https://martinuke0.github.io/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E Hugo -- 0.152.2 en Thu, 17 Sep 2026 10:01:26 +0000 Hands‑On Build: Mixture‑of‑Experts Top‑K Gating Router in Pure Python https://martinuke0.github.io/posts/2026-09-17-handson-build-mixtureofexperts-topk-gating-router-in-pure-python/ Thu, 17 Sep 2026 10:01:26 +0000 https://martinuke0.github.io/posts/2026-09-17-handson-build-mixtureofexperts-topk-gating-router-in-pure-python/ Build a pure‑Python mixture‑of‑experts router with top‑k gating and auxiliary load‑balancing loss – a hands‑on project that demonstrates systems‑level ML engineering skill. Hands‑On Build Guide: Page‑Transformer Inference with Greedy KV‑Cache Eviction and Paged Attention in Numpy https://martinuke0.github.io/posts/2026-09-16-handson-build-guide-pagetransformer-inference-with-greedy-kvcache-eviction-and-paged-attention-in-numpy/ Wed, 16 Sep 2026 16:01:49 +0000 https://martinuke0.github.io/posts/2026-09-16-handson-build-guide-pagetransformer-inference-with-greedy-kvcache-eviction-and-paged-attention-in-numpy/ Build a minimal page‑transformer inference engine from scratch using NumPy, demonstrating greedy KV‑cache eviction and paged attention for a portfolio project that signals systems skills to hiring managers. Hands‑On Build Guide: Pure‑Python Safetensors Parser & Weight Shard Assembler with mmap Lazy Loading https://martinuke0.github.io/posts/2026-09-16-handson-build-guide-purepython-safetensors-parser-weight-shard-assembler-with-mmap-lazy-loading/ Wed, 16 Sep 2026 12:00:59 +0000 https://martinuke0.github.io/posts/2026-09-16-handson-build-guide-purepython-safetensors-parser-weight-shard-assembler-with-mmap-lazy-loading/ Build a pure‑Python safetensors parser and weight shard assembler that uses mmap for lazy loading – a concrete, runnable project that signals systems engineering skill on a CV. Hands‑On Build Guide: Pure Python Mixture‑of‑Experts Router with Load‑Balanced Top‑K Gating https://martinuke0.github.io/posts/2026-09-12-handson-build-guide-pure-python-mixtureofexperts-router-with-loadbalanced-topk-gating/ Sat, 12 Sep 2026 21:01:14 +0000 https://martinuke0.github.io/posts/2026-09-12-handson-build-guide-pure-python-mixtureofexperts-router-with-loadbalanced-topk-gating/ Build a pure‑Python Mixture‑of‑Experts router with load‑balanced top‑k gating from scratch; a hands‑on CV project that demonstrates systems engineering skills. Hands‑On: Building a User‑Safety Service for Your Portfolio https://martinuke0.github.io/posts/2026-09-11-handson-building-a-usersafety-service-for-your-portfolio/ Fri, 11 Sep 2026 14:01:15 +0000 https://martinuke0.github.io/posts/2026-09-11-handson-building-a-usersafety-service-for-your-portfolio/ A step‑by‑step guide to building a production‑ready Go service that enforces user‑safety policies, rate‑limits requests, and logs actions – a tangible project that signals systems engineering skill to hiring managers. Hands-On Build Guide: QLoRA Fine‑Tuner From Scratch in PyTorch with NF4 Quantization and LoRA Merging https://martinuke0.github.io/posts/2026-09-11-hands-on-build-guide-qlora-finetuner-from-scratch-in-pytorch-with-nf4-quantization-and-lora-merging/ Fri, 11 Sep 2026 12:00:50 +0000 https://martinuke0.github.io/posts/2026-09-11-hands-on-build-guide-qlora-finetuner-from-scratch-in-pytorch-with-nf4-quantization-and-lora-merging/ Build a QLoRA fine‑tuner from scratch in PyTorch, implementing NF4 4‑bit quantization and LoRA weight merging for efficient CV model customization. Pure‑Python Paged Attention KV‑Cache Manager: LRU & Random Eviction https://martinuke0.github.io/posts/2026-09-11-purepython-paged-attention-kvcache-manager-lru-random-eviction/ Fri, 11 Sep 2026 09:00:57 +0000 https://martinuke0.github.io/posts/2026-09-11-purepython-paged-attention-kvcache-manager-lru-random-eviction/ Hands‑on guide to building a pure‑Python paged attention KV‑cache manager with LRU and random eviction, a concrete portfolio project that demonstrates systems‑level engineering skill for CVs and interviews. Hands-On Build Guide: Pure‑Python GGUF Weight Loader with Lazy Memory‑Mapped Tensor Initialization https://martinuke0.github.io/posts/2026-09-10-hands-on-build-guide-purepython-gguf-weight-loader-with-lazy-memorymapped-tensor-initialization/ Thu, 10 Sep 2026 22:00:31 +0000 https://martinuke0.github.io/posts/2026-09-10-hands-on-build-guide-purepython-gguf-weight-loader-with-lazy-memorymapped-tensor-initialization/ Build a pure‑Python GGUF weight loader with lazy memory‑mapped tensor initialization. A hands‑on side project that shows systems‑level skill for CV and ML roles. Build a LoRA Adapter Layer from Scratch in PyTorch https://martinuke0.github.io/posts/2026-09-10-build-a-lora-adapter-layer-from-scratch-in-pytorch/ Thu, 10 Sep 2026 21:01:13 +0000 https://martinuke0.github.io/posts/2026-09-10-build-a-lora-adapter-layer-from-scratch-in-pytorch/ Implement a LoRA adapter from scratch in PyTorch, covering low‑rank decomposition, forward injection, and merge/unmerge for inference. Full runnable code included. Hands-On Build Guide: Quantization‑Aware Portfolio Project for Engineering CV https://martinuke0.github.io/posts/2026-09-09-hands-on-build-guide-quantizationaware-portfolio-project-for-engineering-cv/ Wed, 09 Sep 2026 16:01:54 +0000 https://martinuke0.github.io/posts/2026-09-09-hands-on-build-guide-quantizationaware-portfolio-project-for-engineering-cv/ Build a production‑ready quantization pipeline for LLM inference and add a runnable project to your CV that signals real systems skill.