Get to know Nicolay Christopher Gerold
I'm an AI engineer specializing in building practical AI solutions with LLMs. I've been working with foundation models since 2019 and have seen what works and what doesn't.
I started in 2019 finetuning encoder-decoder models for clustering and classification. After the GPT-3 release, I recognized the immense potential and went all-in on LLMs, freelancing on information extraction in healthcare and insurance before building financial report generation agents.
Now, I build complex workflows and AI agents that combine search, traditional machine learning, and foundation models to take over specific business tasks.
Selected Projects
Insurance Search Enhancement
LLM-powered search for a large insurance company. 15% increase in nDCG and sped up time to contract by 5%.
Financial Analysis Agent
Agent for financial report analysis for a Swiss bank to improve decision making support.
Healthcare Data Extraction
LLM-powered data extraction for a healthcare startup tackling electronic health records. Improved accuracy by 12% and reduced cost by 24%.
M&A Due Diligence Automation
Agent for M&A due diligence replacing 100+ hours of manual work.
Customer Support Classification
Automated customer support classification system for a telecom provider. Reduced response time by 67% and improved first-contact resolution rate from 76% to 91%.
Legal Document Search Engine
Semantic search engine for legal documents, processing 2M+ contracts. Reduced discovery time by 67% and saved $200K in annual review costs.
Podcast Appearances
How AI Is Built
My own podcast where I interview the best builders in the AI space.
Why you shouldn't finetune?
on For Sake of Search by David Tippett
How to Make LLMs Boring (Predictable, Reliable, and Safe)
on The Data Stack Show by RudderStack
Beyond Code: AI Data & Design
on AI or Die by AlignAI
Technology Stack
These are the tools and technologies I use to build practical AI solutions:
My Tech Stack
My toolkit for building intelligent, scalable AI solutions