Felipe O.

Key Skills

Software

No software listed

Top Subject Matter

Public Bidding Documents / Legal AI

Dynamic Narrative/Video Game AI

Top Data Types

Text

Top Task Types

Entity (NER) Classification

Text Generation

Freelancer Overview

AI Researcher & Developer | Study Group. Brings 2+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal and Proprietary Tooling. Education includes Bachelor of Technology, FATEC (Faculty of Technology) (2023) and Technical Degree, ETEC (State Technical School) (2020). AI-training focus includes data types such as Text and labeling workflows including Entity (NER) Classification and Text Generation.

Labeling Experience

Game Development & Local AI Integration | Senior Project (TCC)

TextText Generation

Researched, implemented, and tested local Large Language Model (LLM) inference within video game environments using Ren'Py. Created dynamic scripts and narrative datasets to be processed by local LLMs for unscripted, AI-generated in-game dialog. Focused on ensuring that the AI-generated text responses preserved both real-time performance and narrative coherence.• Developed and tuned datasets for in-game text generation by LLMs. • Integrated LLM inference pipelines with proprietary game dialog systems. • Collected annotation feedback from AI-generated interactions to refine model outputs. • Ensured real-time AI text generation capability under hardware resource constraints.

2026 - Present

AI Researcher & Developer | Study Group

TextEntity (NER) Classification

Developed and enhanced a Python-based Retrieval-Augmented Generation (RAG) system focused on the automated extraction and analysis of public bidding document text. Built complex workflows to parse and embed unstructured textual data for AI processing, enabling downstream labeling within RAG pipelines. Customized open-source tools to maintain full data privacy locally, bypassing external dependencies.• Automated data extraction and parsing of public document text for entity recognition and classification tasks. • Integrated and adapted open-source tools for advanced text NER and embedding workflows. • Ensured privacy and compliance through 100% local data processing infrastructure. • Contributed to enhanced training datasets for language models in legal and public administration domains.

2026 - Present

Education

Work History