Kelvin Amoaba
Software engineer building scalable systems and exploring the depths of low-level architecture. Currently at Vela Partners.
CoFEE: Reasoning Control for LLM-Based Feature Discovery
A framework for automating feature discovery from unstructured data using LLMs with cognitive constraints, inducing reasoning behaviors like backward chaining from outcomes and verification against data leakage criteria. Achieves 15.2% higher success rate, 29% fewer features generated, and 53.3% cost reduction over vanilla LLM approaches.
Maximilian Westermann, Ben Griffin, Aaron Ontoyin Yin, Zakari Salifu, Yagiz Ihlamur, Kelvin Amoaba, Joseph Ternasky, Fuat Alican, Yigit Ihlamur · arXiv 2026
VCBench: Benchmarking LLMs in Venture Capital
The first benchmark for predicting founder success in venture capital, providing 9,000 anonymized founder profiles. State-of-the-art LLMs like DeepSeek-V3 deliver over 6x baseline precision, with most models surpassing human benchmarks.
Rick Chen, Joseph Ternasky, Afriyie Samuel Kwesi, Ben Griffin, Aaron Ontoyin Yin, Zakari Salifu, Kelvin Amoaba, Xianling Mu, Fuat Alican, Yigit Ihlamur · arXiv 2025
From Limited Data to Rare-event Prediction: LLM-powered Feature Engineering and Multi-model Learning in Venture Capital
A framework for predicting rare, high-impact outcomes by integrating large language models with a multi-model machine learning architecture for venture capital decision-making.
Mihir Kumar, Aaron Ontoyin Yin, Zakari Salifu, Kelvin Amoaba, Afriyie Kwesi Samuel, Fuat Alican, Yigit Ihlamur · arXiv 2025
AI-powered analyst agents for VCs. Built autonomous LLM-based agents to automate early-stage tasks like pitch deck analysis, market research, and investment memo generation—drastically reducing due diligence time.
A full-stack self-healing web scraper that leverages AI to automate complex web scraping workflows—over 10 million records collected, with a 90% reduction in manual data collection.