From $200 to $30: Five Layers of LLM Cost Optimization

Fri, 24 Apr 2026 12:00:00 +0200

A walkthrough of how I cut an LLM-based product classifier's token usage by ~92% through compression, two-stage prompting, exact-match lookups, similarity caching, and batching.

What the Hell Are Layer2 Rollups

Thu, 05 Jun 2025 11:24:33 +0200

What the Hell Are Layer2 Rollups?

If you’ve spent any time in the Ethereum or blockchain space, you’ve probably heard the term “Layer 2” thrown around—often in the same breath as “rollups.” But what does it actually mean? Why is everyone so excited about it? And why should anyone building on blockchain care?

The Problem: Ethereum’s Scaling Bottleneck

Ethereum is the world’s most popular smart contract platform, but it’s not without its flaws. The biggest? Scalability. The base layer (Layer 1) can only handle about 15-30 transactions per second: When demand spikes, fees skyrocket and the network slows to a crawl. Not exactly the “world computer” we all dream about.

About

Wed, 28 May 2025 00:00:00 +0000

Hi, I’m Dariusz Dwornikowski

Engineering leader with 20+ years of experience scaling tech companies, building products, and leading technical organizations. Track record of 2 successful M&A exits (IBM, HIG Growth) and growing teams from 0 to 400+. Based in Poznań, Poland.

Currently founder of Bitropy — sovereign AI infrastructure, agentic apps, and AI integration for enterprises.

Experience

Founder — Bitropy (2025 – now). Sovereign AI infrastructure, agentic apps and AI integration for enterprises.
CTO — WorkSuite Inc (2022 – 2025). Led engineering & infosec. Key contributor to acquisition by HIG Growth.
VP Engineering / CTO Poland — Nordcloud, an IBM Company (2017 – 2022). Member of the global leadership team. Set up Nordcloud Poland from 0 to 400 people. Scaled product engineering to 150+. Part of the team behind the successful exit to IBM.
Co-Founder & Technology Director — Tenesys (2015 – 2017). AWS cloud implementations, video/voice streaming, IoT, and enterprise migrations.
Researcher — Poznan University of Technology (2009 – now). Distributed systems, process calculi, IEEE publications.

What I Know

AI & agentic systems — AI transformation, agentic coding adoption, MCP infrastructure, LLM integration
Cloud architecture — AWS, Google Cloud, multi-cloud (AWS Solutions Architect Associate, GCP Architect Professional, FinOps Certified Practitioner)
Platform & infra — Kubernetes, containerization, CI/CD, distributed systems
Engineering leadership — scaling teams from 0 to 400+, two M&A exits, 5 enterprise SaaS products bootstrapped at Nordcloud, 5+ advisory board roles
Open source — Debian Developer since 2015
Academia — almost PhD in distributed systems (restarting it)

I Can Help With

AI transformation consulting — end-to-end guidance on transforming engineering organizations into AI-driven teams using agentic coding, LLMs, and AI process integration
Fractional CTO — strategic technology leadership and hands-on technical guidance for scaling engineering organizations
Advisory board — board-level advisory on scaling engineering, product development, technical strategy, and M&A preparation
Exit strategy & M&A — preparing tech companies for successful acquisition, drawing on direct experience with IBM and HIG Growth exits

Why This Blog?

I believe in learning publicly. By sharing what I’m working on, I hope to help other technical leaders navigating AI transformation and connect with like-minded professionals.

Darek's Blog