Solomon Akinmoji

I’m an AI/ML Quality Engineer with strong experience in NLP, ASR evaluation, and search relevance. I focus on improving model performance through evaluation frameworks, quality analysis, and consistent data labeling.

In my current role, I evaluate NLP and ASR model outputs for accuracy, fluency, and intent alignment. I design annotation guidelines to strengthen labeling consistency and run error analysis to pinpoint model weaknesses and drive better results.

Previously, I worked as a Voice Search & Content NLP Quality Analyst at TCS, where I annotated and evaluated voice search queries for intent classification. I also improved dataset quality and collaborated with global teams on AI data pipelines.

I started my quality work in search and ads at CapCut (ByteDance), assessing search relevance and ad quality. Across these roles, I’ve built a grounded approach to evaluation, using Python and large-scale data workflows to support high-impact AI systems.