Kristian Garza
AI Software Engineer · Product Designer · Open Science
Senior AI Software Engineer at Digital Science, Berlin
- LLM APIs & agents
- Knowledge graphs
- MCP
- Open science infrastructure
- Design systems
- Product design
About
Building and prototyping AI-driven microservices and agents at Digital Science, from LLM-powered APIs to Rust-based clustering engines.
Developed core infrastructure at DataCite, including Commons, Fabrica, and Sashimi, while leading metadata and design system initiatives.
Hosting DS’s AI Technology Radar sessions and experimenting with personal AI projects like a Dataset Discovery & Evaluation Agent.
Worked with
Selected work
Case studies
-
01
Query Translation API - Natural Language to Database Queries
Architected and launched a FastAPI microservice that turns natural-language requests into optimized Dimensions searches.
-
02
Harmonizing with a Design System
Crafted a Design System for all DataCite frontend services.
-
03
Innovating Data Usage Processing Services
Pioneering an alternative to existing data usage processing services through web tracker development.
-
04
Usage Reports API - Research Data Metrics at Scale
Designed and delivered Sashimi—a Rails API that ingests, validates, and stores large SUSHI usage reports at 50,000-dataset scale.
-
05
Redesigning DataCite's Harvesting Services
Redesigned DataCite's Harvesting Services from the ground up to boost service utilization and unlock new revenue opportunities.
Side projects
Useful things I've built
-
An AI agent automating discovery, evaluation, and acquisition of open research datasets for scientists and data engineers.
-
An asynchronous AI development tool where you write task specifications and receive completed pull requests overnight — delegation without presence.
-
A personal technology radar that categorizes tools, frameworks, and techniques into Adopt, Trial, and other tiers — separating what's genuinely useful from what's just hype.
-
A Python toolkit that uses GPT-3/3.5 to translate, enrich, and cross-walk bibliographic metadata across schemas, with CLI and CI/CD support.
Ongoing
Technology Radar
Tools, frameworks and techniques sorted into Adopt, Trial, Assess and Hold, the same format as the AI Technology Radar sessions I host at Digital Science.
Research
Publications
- 2023
- 2023
- 2023
- 2023
- 2023