For employers

Hire this AI Trainer

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

LoginCreate account
Invite to Job
W

Wilfred Gomez

Prompt Engineering and LLM Integration Specialist

USA flag
Orlando, Usa
$20.00/hrExpertLabelboxScale AIRemotasks

Key Skills

Software

LabelboxLabelbox
Scale AIScale AI
RemotasksRemotasks
Surge AISurge AI
TolokaToloka
AWS SageMakerAWS SageMaker
Data Annotation TechData Annotation Tech
MindriftMindrift
OneFormaOneForma
MercorMercor

Top Subject Matter

AI application prompt engineering
workforce management
operational optimization

Top Data Types

TextText
DocumentDocument

Top Task Types

Prompt Response Writing SFT
Classification
Computer Programming Coding
RLHF

Freelancer Overview

Prompt Engineering and LLM Integration Specialist. Brings 8+ 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, University of Central Florida (2019). AI-training focus includes data types such as Text and labeling workflows including Prompt + Response Writing (SFT).

ExpertEnglish

Labeling Experience

Prompt Engineering and LLM Integration Specialist

TextPrompt Response Writing SFT
Developed and engineered prompt templates and LLM interaction patterns for workforce management and multi-agent orchestration AI. Designed, evaluated, and maintained enterprise-ready prompt libraries supporting context-aware, grounded AI with real-world operations data. Integrated Model Context Protocol to ensure accurate, reliable LLM output and used AI developers tools to accelerate creation and review of prompt-driven features. • Created, managed, and version-controlled 50+ production prompts for AI agent tasks • Systematic evaluation and regression testing of prompt and response quality • Iterative prompt tuning and error analysis for enterprise AI use cases • Integrated outputs with OpenAI, Anthropic, and LangChain frameworks

Developed and engineered prompt templates and LLM interaction patterns for workforce management and multi-agent orchestration AI. Designed, evaluated, and maintained enterprise-ready prompt libraries supporting context-aware, grounded AI with real-world operations data. Integrated Model Context Protocol to ensure accurate, reliable LLM output and used AI developers tools to accelerate creation and review of prompt-driven features. • Created, managed, and version-controlled 50+ production prompts for AI agent tasks • Systematic evaluation and regression testing of prompt and response quality • Iterative prompt tuning and error analysis for enterprise AI use cases • Integrated outputs with OpenAI, Anthropic, and LangChain frameworks

2022 - Present

LLM Data Labeling and Evaluation Lead

TextPrompt Response Writing SFT
Built and managed LLM-powered natural language query systems, including architecture and evaluation of prompt/response pairs. Introduced and supervised OpenAI API and LangChain workflows to provide document semantic search, retrieval-augmented generation, and QA labeling. Oversaw dataset preparation, transformation, and creation of ground truth labels for business and analytics applications. • Created datasets and prompts for query answering and RAG pipelines • Evaluated and rated LLM-generated responses for accuracy and reliability • Managed integration and prompt tuning with OpenAI embeddings and Pinecone • Conducted iterative feedback cycles improving business insight features

Built and managed LLM-powered natural language query systems, including architecture and evaluation of prompt/response pairs. Introduced and supervised OpenAI API and LangChain workflows to provide document semantic search, retrieval-augmented generation, and QA labeling. Oversaw dataset preparation, transformation, and creation of ground truth labels for business and analytics applications. • Created datasets and prompts for query answering and RAG pipelines • Evaluated and rated LLM-generated responses for accuracy and reliability • Managed integration and prompt tuning with OpenAI embeddings and Pinecone • Conducted iterative feedback cycles improving business insight features

2020 - 2022

AI Chatbot Prompt/Evaluation Associate

TextPrompt Response Writing SFT
Contributed to experiments with automated content generation, LLM prompt prototyping, and chatbot fine-tuning on the GPT-3 API. Led early data labeling and evaluation efforts for AI chat response systems in a customer service context. Validated model output, reviewed generated text, and iteratively refined training data and system prompts. • Labeled and evaluated chatbot interaction datasets for quality • Provided feedback on model reliability and fit for SMB support needs • Assisted in assembling training/test sets for content generation evaluation • Supported documentation and process improvement for early AI use cases

Contributed to experiments with automated content generation, LLM prompt prototyping, and chatbot fine-tuning on the GPT-3 API. Led early data labeling and evaluation efforts for AI chat response systems in a customer service context. Validated model output, reviewed generated text, and iteratively refined training data and system prompts. • Labeled and evaluated chatbot interaction datasets for quality • Provided feedback on model reliability and fit for SMB support needs • Assisted in assembling training/test sets for content generation evaluation • Supported documentation and process improvement for early AI use cases

2019 - 2020

Education

U

University of Central Florida

Bachelor of Science, Computer Science

Bachelor of Science
2015 - 2019

Work History

N

NovaSpark Technologies

Senior Full-Stack Engineer

Orlando
2022 - Present
M

Meridian Analytics Group

Software Engineer

Tampa
2020 - 2022