For employers

Hire this AI Trainer

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

Invite to Job
Ryota Kando

Ryota Kando

LLM Evaluation and Text Generation Specialist in Japanese.

Japan flagYokohama, Japan
$25.00/hrIntermediateAppenGoogle Cloud Vertex AIInternal Proprietary Tooling

Key Skills

Software

AppenAppen
Google Cloud Vertex AIGoogle Cloud Vertex AI
Internal/Proprietary Tooling
Don't disclose

Top Subject Matter

No subject matter listed

Top Data Types

ImageImage
TextText
VideoVideo

Top Task Types

Evaluation Rating
Fine Tuning
Prompt Response Writing SFT
Question Answering
RLHF

Freelancer Overview

As an AI training data specialist, I have a diverse range of project experience, from evaluating language models to image labeling. My core skills are prompt creation and AI response evaluation, where I have gained deep insights into maximizing model performance. In addition, I have hands-on experience fine-tuning models personally, which gives me a deep, technical understanding of AI behavior that goes beyond an evaluator's perspective. Through these experiences, I have directly contributed to model improvement. Furthermore, my experience in various tasks, including fact-checking in Japanese history and image labeling, has equipped me with the flexibility to handle assignments that demand exceptional accuracy and attention to detail. My key strength lies in this unique combination of skills: the ability to work with both text and image data formats, the capability to manage specialized subject matter, and a technical understanding of AI models.

IntermediateEnglishSpanishJavanese

Labeling Experience

AI Chatbot Response Evaluation and Ranking (RLHF)

Don T DiscloseTextRLHF
I evaluated and ranked multiple responses generated by a large language model based on criteria such as accuracy, consistency, and helpfulness. I also crafted diverse prompts to test and train the model's capabilities in various scenarios. This task involved providing human feedback to directly improve the model's conversational abilities.

I evaluated and ranked multiple responses generated by a large language model based on criteria such as accuracy, consistency, and helpfulness. I also crafted diverse prompts to test and train the model's capabilities in various scenarios. This task involved providing human feedback to directly improve the model's conversational abilities.

2024 - 2024

Education

K

Keio University

Bachelor of Archaeology and Ethnology, Archaeology and Ethnology

Bachelor of Archaeology and Ethnology
2024 - 2025

Work History

No Work History added yet

Ryota K. hasn’t added any Work History to their OpenTrain profile yet.