About me


๐Ÿ›ค๏ธ Who I am: My name is David Streuli, and I am a bioinformatics specialist with five formative years in Taiwan, where I chose to conclude my PhD studies to focus on AI and knowledge extraction systems.

๐Ÿ”ฅ Past 5 years:I have 2 years of experience in AI-driven pipeline development. This includes Python, LLM systems, and knowledge graphs. In NLP research, I mastered LLM pipeline development, dataset curation, and graph database utilization. In the first half of my PhD, I developed a gene-sequence optimization algorithm, investigated biological evolution prediction and joined a GWAS (genome-wide association studies) project.

๐Ÿ’ก Key skills: I’m an expert in Python pipelines for data analysis and LLM systems. My skills include statistical modeling, scientific documentation, and information extraction. I specialize in relation extraction, entity linking, data gathering, fact-checking, and LLM agentic systems.

๐ŸŒ My value and drive: I believe in democratizing knowledge through better search tools. These tools help people find and understand scientific information more easily.

๐Ÿ“Š My Agenda: I spend 70% of my time as a freelancer. My projects involve data gathering, fact-checking, information extraction, and LLM agentic systems. The other 30% goes to a semantic search project. This project builds a tool to automate information extraction from scientific literature. It converts text into knowledge graphs and machine-readable formats. This makes finding specific information easier without reading entire papers.

๐Ÿ“… Still interested? If you’re interested in speaking with me about NLP innovation, next-generation semantic search, or knowledge graph applications, please send me a brief message and connect with me.

What I’m doing

Mission: Make information free

The most critical issue in science, is the growing cliff between recorded and accessible information. As we enter the fourth industrial revolution, with autonomous robotic workforces on the horizon, Iโ€™m more committed than ever to staying ahead of the curve.

The future ——> is here!

Text-Graph-Translation

I’m currently dedicated to elevate pressure from the issue of information inaccessibility. —>

AI blog

As my work includes AI, here I reflect on recent AI developements, new tools and technologies that are about to surface to the public.—>

Career

texxt .—>

The most critical issue in science, is the growing cliff between recorded and accessible information. As we enter the fourth industrial revolution, with autonomous robotic workforces on the horizon, Iโ€™m more committed than ever to staying ahead of the curve.

The Data Haiku

Data’s dark divide,
grow AI bridges,
the knowledge gap,
Science’s new frontier.

Here it’s going to be more interesting:

The most recent posts

ready, set, go:

Follow me on LinkedIn for updates!