For employers

Hire this AI Trainer

Sign in or create an account to invite AI Trainers to your job.

LoginCreate account
Invite to Job
P
Peter Johnson

Peter Johnson

RLHF Fine-Tuning Data Annotator

Kenya flagNairobi, Kenya
$40.00/hrIntermediateMercor

Key Skills

Software

MercorMercor

Top Subject Matter

AI generated text/content
AI text generation evaluation
Prompt engineering and SFT training data

Top Data Types

TextText
DocumentDocument

Top Task Types

Prompt + Response Writing (SFT)Prompt + Response Writing (SFT)

Freelancer Overview

RLHF Fine-Tuning Data Annotator. Brings 7+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal and Proprietary Tooling. AI-training focus includes data types such as Text and labeling workflows including Evaluation, Rating, and Prompt + Response Writing (SFT).

IntermediateEnglish

Labeling Experience

Prompt Engineering and SFT Dataset Contributor

TextPrompt Response Writing SFT
Developed structured prompt templates for AI model fine-tuning and supervised training. Authored and validated prompt-response pairs to facilitate supervised fine-tuning of language models. Focused on semantic clarity, task alignment, and consistency across diverse scenarios.• Built prompt template libraries for varied use cases. • Ensured JSON Schema conformity for structured outputs. • Enabled reliable downstream data parsing for integration. • Enhanced supervised learning pipelines for LLMs.

Developed structured prompt templates for AI model fine-tuning and supervised training. Authored and validated prompt-response pairs to facilitate supervised fine-tuning of language models. Focused on semantic clarity, task alignment, and consistency across diverse scenarios.• Built prompt template libraries for varied use cases. • Ensured JSON Schema conformity for structured outputs. • Enabled reliable downstream data parsing for integration. • Enhanced supervised learning pipelines for LLMs.

2021 - 2023

AI Content Quality Evaluator

Text
Designed and implemented quality evaluation rubrics for AI-generated content. Conducted human-in-the-loop review sessions to evaluate content meeting multiple qualitative criteria. Regularly participated in A/B testing frameworks to optimize model outputs.• Created 30+ rubrics for accuracy, tone, and compliance. • Performed 500+ prompt evaluation sessions weekly. • Reduced manual QA hours through structured review cycles. • Improved model output reliability scores through feedback.

Designed and implemented quality evaluation rubrics for AI-generated content. Conducted human-in-the-loop review sessions to evaluate content meeting multiple qualitative criteria. Regularly participated in A/B testing frameworks to optimize model outputs.• Created 30+ rubrics for accuracy, tone, and compliance. • Performed 500+ prompt evaluation sessions weekly. • Reduced manual QA hours through structured review cycles. • Improved model output reliability scores through feedback.

2021 - 2023

RLHF Fine-Tuning Data Annotator

Text
Reviewed and annotated AI generated responses against established quality benchmarks. Directly contributed to the creation of RLHF fine-tuning datasets for internal language models. Systematically evaluated accuracy, tone, and structure to support AI training refinement.• Reviewed and labeled over 10,000 AI responses for dataset quality purposes. • Applied quality rubrics to align annotations with model training needs. • Used structured prompt evaluation methods for consistency. • Collaborated with engineering teams to define gold standards.

Reviewed and annotated AI generated responses against established quality benchmarks. Directly contributed to the creation of RLHF fine-tuning datasets for internal language models. Systematically evaluated accuracy, tone, and structure to support AI training refinement.• Reviewed and labeled over 10,000 AI responses for dataset quality purposes. • Applied quality rubrics to align annotations with model training needs. • Used structured prompt evaluation methods for consistency. • Collaborated with engineering teams to define gold standards.

2021 - 2023

Education

J

JKUAT

COMPUTER SCIENCE, JKUAT

COMPUTER SCIENCE
2018 - 2024

Work History

N

N/A

Senior AI Workflow Engineer

Nairobi
2023 - Present
N

N/A

LLM Integration Specialist

Nairobi
2021 - 2022