Finian O.

Key Skills

Software

Don't disclose

Other

Data Annotation Tech

Google Cloud Vertex AI

Top Subject Matter

AI language model evaluation for NLP tasks (generation, translation, summarization, QA)

bias and quality assessment

AI language model evaluation and feedback for NLP text quality

Top Data Types

Text

Computer Code Programming

Top Task Types

Evaluation/Rating

Transcription

Prompt + Response Writing (SFT)

Freelancer Overview

Artificial Intelligence (AI) Engineer, Tencent (AI Language Model Evaluator). Brings 7+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Don't disclose and Other. Education includes N/A, Federal Polytechnic, Oko Anambra State (2018). AI-training focus includes data types such as Text and labeling workflows including Evaluation and Rating.

Labeling Experience

Artificial Intelligence (AI) Engineer, Tencent (AI Language Model Evaluator)

Don't discloseText

Performed evaluation of AI language model outputs across tasks including text generation, translation, summarization, and question answering. Assessed coherence, fluency, overall quality, and bias presence in generated text. Provided structured judgments to help ensure outputs align with human expectations and high accuracy standards. • Rated/assessed generated text quality (coherence and fluency) • Reviewed outputs for bias and potential ethical issues • Evaluated performance across multiple NLP task types • Supported iterative improvements through quality evaluation

2021 - 2024

Associate Artificial Intelligence (AI) Engineer, Stack

OtherText

Assisted in evaluating and improving AI language model performance by reviewing AI-generated text quality. Offered constructive feedback to help developers enhance model outputs to meet accuracy, relevance, and human-like standards. Updated knowledge of evolving language model evaluation techniques to inform ongoing assessments. • Provided feedback to AI developers on model output quality • Checked that generated text is accurate and relevant • Monitored human-like quality expectations • Applied/evolved evaluation approaches using new techniques

2018 - 2021

Education

Work History