Njissang Yogongi

I’m a senior technology professional with 20+ years in software engineering and data systems, now specializing in AI model evaluation and LLM quality assessment. I apply analytical thinking, prompt engineering, and RLHF-aligned evaluation methodologies to evaluate LLM outputs for factual accuracy, coherence, and bias.

In my current AI Evaluation Specialist role, I developed data annotation guidelines that improved inter-annotator agreement by 18% and authored evaluation reports for technical and non-technical stakeholders. I also lead data annotation and labeling workflows for internal ML training datasets, establishing company-wide quality assurance standards for model evaluation presentations.

Previously, as a Senior Data Engineer, I defined evaluation metrics and benchmark test suites for predictive models, built Python/SQL automation tools that reduced manual QA effort by 40%, and mentored 6 junior engineers. Across my work, I’ve documented 200+ edge-case failures that inform model quality improvements, translating those insights into clear, actionable recommendations.