Build yourself flowers

2026-04-20 · Source: Tech Blog on ✰Vicki Boykis✰ · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics, Software Development & Engineering · Depth: Intermediate, extended

Summary

Vicki Boykis's keynote from the April 2026 Applied Machine Learning Conference explores the enduring relevance of traditional machine learning engineering amidst the rise of large language models (LLMs). She argues that technical excellence remains crucial, drawing parallels to Dutch Golden Age flower painter Rachel Ruysch, who achieved mastery through lifelong practice, mentorship, and experimentation. Boykis illustrates this by detailing her process for building "Rijksearch," a semantic search engine for Rijksmuseum art. This project involved using multimodal data, Gemini API for embeddings, Redis vector sets with HNSW for indexing, and a Go-based web app. While LLMs assisted with tasks like front-end scaffolding, Go language concepts, and data formatting, core architectural decisions and complex system understanding stemmed from human experience, reinforcing that true mastery and "data sense" are cultivated over years, not automated.

Key takeaway

For AI Engineers and ML Architects evaluating LLM integration, recognize that while AI tools accelerate specific tasks like front-end development or data scripting, your deep "data sense" and architectural expertise remain irreplaceable. Focus on cultivating mastery in core system design, understanding latency constraints, and selecting appropriate data structures (e.g., Redis vector sets with HNSW) through deliberate practice. This ensures robust, high-quality systems, preventing the degradation of engineering quality seen in over-outsourced scenarios.

Key insights

Technical mastery in ML engineering, like art, requires deep practice and human intuition, not just LLM-driven automation.

Principles

• Technical excellence prevents systemic failures and cost overruns.
• Software engineering is a craft requiring sustained, deliberate practice.
• Mastery involves mentorship, continuous learning, and remixing ideas.

Method

The author built a semantic search engine (Rijksearch) using multimodal data, Gemini API embeddings, Redis vector sets with HNSW, and a Go web app, iteratively applying new technologies while leveraging AI for specific, smaller tasks.

In practice

• Use LLMs for front-end scaffolding and data formatting scripts.
• Learn new languages by combining books, examples, and LLM concept explanations.
• Prioritize human experience for architectural decisions and complex system design.

Topics

• Machine Learning Engineering
• Large Language Models
• Semantic Search
• Embeddings
• Redis Vector Sets
• Go Programming
• Technical Mastery

Code references

• veekaybee/what_are_embeddings

Best for: AI Engineer, Machine Learning Engineer, Director of AI/ML

Related on AIssential

• We Are Getting So Much Wrong With Current AI — The rise of LLMs in AI development diminishes the need for deep technical understanding and hands-on optimization, reducing intellectual challenge.
• [AINews] Claude Sonnet 4.6: clean upgrade of 4.5, mostly better with some caveats — The AI engineering field seeks a "standard model" to guide development, moving from demos to production-ready applications.
• "Something Big is Happening." This quarter has a start-up vibe: LLM experiments, great projects, and new optimization material — Rapid AI advancements necessitate immediate curriculum retooling to provide students with practical, hands-on LLM experience.
• Data Engineering for the LLM Age — LLM performance fundamentally depends on high-quality, AI-ready data engineering across training, inference, and evaluation.
• Building AI with AI — LLMs should be used to build systems, not as systems, reinforcing code's critical role.
• Feature Engineering with LLMs: Techniques & Python Examples — LLMs automate semantic feature engineering, transforming raw data into context-rich representations for improved ML performance.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Tech Blog on ✰Vicki Boykis✰.