John “.

Key Skills

Software

Mindrift

Telus

Toloka

Other

Top Subject Matter

Large Language Models (LLMs)

reinforcement learning from human feedback (RLHF)

dataset curation

Top Data Types

Text

Document

Image

Top Task Types

RLHF

Fine-tuning

Prompt + Response Writing (SFT)

Bounding Box

Object Detection

Text Generation

Question Answering

Classification

Freelancer Overview

AI Training Specialist focused on LLM performance improvement via RLHF data curation and quality auditing.. Core strengths include Other. Education includes Certificate in Artificial Intelligence, MP LEE and Certificate in Prompt Engineering, Coursera. AI-training focus includes data types such as Text and labeling workflows including RLHF, Fine-tuning, and Prompt + Response Writing (SFT).

Labeling Experience

AI Training Specialist delivering prompt engineering and prompt-response writing for model training and evaluation.

OtherTextPrompt + Response Writing (SFT)

Developed sophisticated prompt templates and associated prompt-response examples to elicit higher reasoning capabilities from generative models. Produced task-based documentation and gold standard responses used for training and benchmarking. Ensured the prompts and outputs reflected consistent instructions and desired answer qualities. • Created prompt templates designed to guide model reasoning effectively. • Generated or curated gold standard prompt-response pairs for SFT-style usage. • Wrote clear task documentation supporting benchmark and training preparation. • Audited response quality to reduce hallucinations and tone/safety issues.

Present

AI Training Specialist specializing in SFT/ranking model data preparation and refinement.

OtherTextFine-tuning

Performed supervised fine-tuning (SFT)-aligned data preparation with emphasis on ranking model accuracy and failure analysis. Leveraged fine-tuning and ranking insights to correct setbacks related to safety, correctness, and tone. Prepared gold-standard targets and training examples to strengthen benchmarking performance. • Authored or curated training data to support SFT and ranking objectives. • Audited and refined labels to improve accuracy, safety, and linguistic tone. • Conducted quality checks against gold standard responses for evaluation. • Applied feedback from ranking outcomes to refine training datasets.

Present

AI Training Specialist focused on LLM performance improvement via RLHF data curation and quality auditing.

OtherTextRLHF

Engaged in RLHF-oriented data work to improve Large Language Model behavior and alignment with human preferences. Focused on producing and curating high-quality training inputs that reduce hallucinations and improve accuracy, safety, and tone. Worked on maintaining consistency between model outputs and nuanced human communication requirements. • Curated datasets and auditing processes to identify and mitigate bias. • Iterated on reward/feedback style signals aligned to desired reasoning quality. • Evaluated outputs for safety and tone compliance during training data preparation. • Supported RLHF pipelines through prompt and response quality control.

Present

Education

Work History