Daniel Olakanmi

Key Skills

Software

Appen

Top Subject Matter

No subject matter listed

Top Data Types

Audio

Computer Code Programming

Document

Geospatial Tiled Imagery

Image

Video

Top Label Types

Entity Ner Classification

Evaluation Rating

Segmentation

Translation Localization

Freelancer Overview

I am a detail-oriented AI evaluation analyst with hands-on experience in data annotation, content labeling, and prompt engineering for AI training and model assessment. My work involves reviewing AI-generated outputs for accuracy, safety, and alignment with user intent, as well as developing test cases to evaluate model reasoning and behavior across various domains. I am skilled at detecting biases, hallucinations, and safety vulnerabilities, and I excel at compiling clear evaluation reports with actionable feedback to improve AI systems. With a strong foundation in machine learning, neural networks, and applied AI gained through professional certification, I bring analytical thinking, technical documentation, and quality assurance expertise to every project I undertake.

Labeling Experience

Data Annotation

AppenImageEntity Ner ClassificationSegmentation

The project centered on evaluating and enhancing AI agent performance across diverse real-world tasks, including question answering, reasoning, content generation, and safety-critical interactions. The objective was to assess outputs for accuracy, relevance, clarity, safety compliance, and alignment with user intent through structured testing, prompt design, and in-depth behavioral analysis to identify and address performance gaps. Evaluated and labeled thousands of AI-generated responses across diverse domains Designed and tested hundreds of structured prompts and edge-case scenarios Followed standardized annotation guidelines and evaluation rubrics Maintained high inter-annotator agreement through consistency checks

The project centered on evaluating and enhancing AI agent performance across diverse real-world tasks, including question answering, reasoning, content generation, and safety-critical interactions. The objective was to assess outputs for accuracy, relevance, clarity, safety compliance, and alignment with user intent through structured testing, prompt design, and in-depth behavioral analysis to identify and address performance gaps. Evaluated and labeled thousands of AI-generated responses across diverse domains Designed and tested hundreds of structured prompts and edge-case scenarios Followed standardized annotation guidelines and evaluation rubrics Maintained high inter-annotator agreement through consistency checks

2023 - 2025

Education

Work History