Viv I.

Key Skills

Software

Other

Top Subject Matter

LLM output evaluation

RLHF & preference ranking

prompt engineering

Top Data Types

Text

Document

Top Task Types

Prompt + Response Writing (SFT)

Freelancer Overview

Freelance AI Trainer & LLM Response Evaluator (Multiple Annotation Platforms). Brings 4+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Internal, Proprietary Tooling, and Other. Education includes Bachelor of Science, University of Lagos (2023). AI-training focus includes data types such as Text and labeling workflows including Evaluation, Rating, and Prompt + Response Writing (SFT).

Labeling Experience

Freelance AI Trainer & LLM Response Evaluator (Multiple Annotation Platforms)

Text

Evaluated, ranked, and rewrote responses from frontier LLMs across reasoning, math, coding, creative writing, and instruction-following tasks using structured rubrics. Produced gold/ideal responses used as supervised fine-tuning data and maintained consistent top-tier quality scores on internal QA audits. Designed adversarial and edge-case prompts to expose hallucinations, refusal failures, and reasoning gaps for ongoing red-team batches. • Performed pairwise preference tasks and multi-turn dialogue evaluations • Managed inter-rater agreement above platform thresholds across multi-week projects • Provided written feedback to refine rubric guidelines • Focused on factuality, citation quality, and rubric-based QA scoring

2023 - Present

Technical Content Writer & Editor (Independent/Agency Clients)

OtherTextPrompt + Response Writing (SFT)

Edited and refined AI-assisted technical drafts for accuracy, voice, and structure, turning writing workflows into outputs suitable for response rewriting and training-support tasks. Researched and fact-checked technical claims across primary and secondary sources to produce citation-clean copy with consistently low revision rates. Supported client deliverables for SaaS and Web3 documentation and explainer content with quality control focused on correctness and clarity. • Refined AI-assisted drafts used for improved response quality • Ensured citation accuracy through fact-checking • Improved technical writing structure for clarity • Maintained low revision rates via careful verification

2022 - 2023

Research & Writing Assistant (Academic/Technical Clients)

Text

Supported evaluation, ranking, and rewriting of frontier LLM outputs across reasoning, math, coding, creative writing, and instruction-following tasks under structured rubrics. Produced gold/ideal responses intended for supervised fine-tuning and conducted quality assurance through internal QA audits. Created adversarial and edge-case prompts to surface hallucination, refusal failures, and reasoning gaps while contributing to red-team prompt batches. • Maintained inter-rater agreement above platform thresholds • Conducted pairwise preference tasks and multi-turn dialogue evaluation • Provided feedback on rubric ambiguity for guideline clarification • Assisted with multi-client academic and technical documentation workflows

2020 - 2022

Education

Work History