For employers

Hire this AI Trainer

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

LoginCreate account
Invite to Job
L

Leonardo Silva

AI Code Evaluation and Prompt Engineering Reviewer

Brazil flagUberlandia, Brazil
$40.00/hrExpert

Key Skills

Software

No software listed

Top Subject Matter

Backend systems
Go code
Payment APIs

Top Data Types

Computer Code ProgrammingComputer Code Programming

Top Task Types

Text SummarizationText Summarization
Question AnsweringQuestion Answering
Object DetectionObject Detection
ClassificationClassification

Freelancer Overview

AI Code Evaluation and Prompt Engineering Reviewer. Brings 11+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal and Proprietary Tooling. Education includes Bachelor of Science, Universidade Estadual de Campinas (2015). AI-training focus includes data types such as Computer Code and Programming and labeling workflows including Evaluation and Rating.

ExpertEnglish

Labeling Experience

AI Code Evaluation and Prompt Engineering Reviewer

I participated in evaluating and reviewing AI-generated Go code and explanations for backend services at Adyen. This work included assessing correctness, readability, and adherence to backend development best practices. Collaboration with AI data teams focused on refining training prompts and validating code generation model responses.• Conducted systematic code review of AI-generated code for payment APIs • Participated in cross-team AI model validation projects focusing on style consistency • Reviewed and refined training prompts for LLMs applied to programming • Documented evaluation guidelines for internal AI tooling

I participated in evaluating and reviewing AI-generated Go code and explanations for backend services at Adyen. This work included assessing correctness, readability, and adherence to backend development best practices. Collaboration with AI data teams focused on refining training prompts and validating code generation model responses.• Conducted systematic code review of AI-generated code for payment APIs • Participated in cross-team AI model validation projects focusing on style consistency • Reviewed and refined training prompts for LLMs applied to programming • Documented evaluation guidelines for internal AI tooling

2020 - Present

AI Code Proposal Reviewer and Dataset Evaluator

At bol.com, I was involved in evaluating and reviewing AI-assisted code proposals and generated code snippets. My responsibilities included providing qualitative feedback to improve the performance of AI code generation systems and clarify code explanations for AI training datasets. I also developed automated pipelines to test and detect errors in AI-generated code.• Reviewed AI-assistance code proposals for idiomatic usage and logical errors • Generated and evaluated code explanations for clarity in training datasets • Developed and maintained testing pipelines for code snippet validation • Collaborated with AI developers on dataset improvement strategies

At bol.com, I was involved in evaluating and reviewing AI-assisted code proposals and generated code snippets. My responsibilities included providing qualitative feedback to improve the performance of AI code generation systems and clarify code explanations for AI training datasets. I also developed automated pipelines to test and detect errors in AI-generated code.• Reviewed AI-assistance code proposals for idiomatic usage and logical errors • Generated and evaluated code explanations for clarity in training datasets • Developed and maintained testing pipelines for code snippet validation • Collaborated with AI developers on dataset improvement strategies

2019 - 2020

AI-Generated Code Peer Reviewer

As a peer reviewer at Avenue Code, I helped assess AI-generated code snippets for readability and correctness. I focused on improving maintainability and supporting the robustness of AI code review tools. My role ensured that codebase and dataset quality stayed high for AI tool development.• Peer-reviewed AI-generated code with a focus on quality and accuracy • Supported robustness testing for AI code review tools • Enhanced code maintainability through best practices documentation • Collaborated on improving code review pipelines

As a peer reviewer at Avenue Code, I helped assess AI-generated code snippets for readability and correctness. I focused on improving maintainability and supporting the robustness of AI code review tools. My role ensured that codebase and dataset quality stayed high for AI tool development.• Peer-reviewed AI-generated code with a focus on quality and accuracy • Supported robustness testing for AI code review tools • Enhanced code maintainability through best practices documentation • Collaborated on improving code review pipelines

2017 - 2019

Education

U

Universidade Estadual de Campinas

Bachelor of Science, Computer Science

Bachelor of Science
2011 - 2015

Work History

A

Adyen

Senior Software Engineer

N/A
2020 - Present
B

bol.com

Software Engineer

N/A
2019 - 2020