// TODO: I’m martinuke0
Welcome to my corner of the internet. This website is a personal blog which I use as a platform to document my learning journey and showcase it for the world to see.
User Safety: Building Secure and Resilient Experiences for Real-World Systems
Exploring concrete user safety patterns, from authentication and authorization to production-grade failure handling, with real-world architectures and actionable takeaways.
Distributed LLM Inference: Parallelism Strategies
Exploring the core parallelism strategies behind distributed LLM inference — tensor, pipeline, data, and expert parallelism — with real-world architecture patterns and practical deployment insights.
Parallelism Strategies: Patterns, Pitfalls, and Production-Ready Approaches
Explore the core parallelism strategies—task, data, pipeline, and model parallelism—and learn how to choose the right pattern for your production workload, with concrete examples from Spark, Ray, Dask, and Kubernetes.
Code as Agent Harness
Code as Agent Harness reframes the relationship between application code and AI agents. Instead of writing prompts, engineers design harnesses — structured code layers that define tools, guardrails, and orchestration logic for autonomous systems.
Backpropagation Demystified: How Neural Networks Actually Learn
Backpropagation is just the chain rule applied to a computational graph. Here’s how it works, why it scales, and how modern frameworks hide the math so you can focus on shipping models.