Harrison B.

Key Skills

Software

AWS SageMaker

Top Subject Matter

LLM application development

semantic search

RAG pipelines

Top Data Types

Text

Top Task Types

Prompt + Response Writing (SFT)

Entity (NER) Classification

Data Collection

Freelancer Overview

Senior AI Software Engineer - Self Employed. Brings 10+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Azure AI Services, OpenAI API, and Pinecone. Education includes Bachelor of Computer Science, Ateneo de Manila University (2017). AI-training focus includes data types such as Computer Code, Programming, and Text and labeling workflows including Prompt + Response Writing (SFT), Fine Tuning, and Named Entity Recognition.

Labeling Experience

Senior AI Software Engineer - Self Employed

AWS SageMakerTextEntity (NER) Classification

Designed and developed AI-powered applications using C# and the .NET platform for enterprise clients. Built production-ready backend services and AI integrations with a focus on reliability and maintainability. Partnered with stakeholders to operationalize ML capabilities and optimize end-to-end system performance in cloud environments. • Built RESTful APIs and microservices for AI solution integration • Integrated large language models, vector databases, and orchestration frameworks into production systems • Developed RAG pipelines and intelligent automation workflows for data processing • Optimized AI inference, prompt engineering, and evaluation processes for quality assurance and security

2024 - Present

Senior AI Software Engineer (Mar 2024 – Present), Self Employed Freelance Remote

Designed and developed enterprise AI powered applications integrating large language models, vector databases, and AI orchestration frameworks into production systems. Developed RAG pipelines and intelligent automation workflows for data processing, then implemented prompt engineering and evaluation processes for quality assurance. Optimized AI systems for scalability, reliability, performance, and security across distributed cloud architectures. • Built RAG pipelines for enterprise data processing and retrieval workflows • Integrated LLMs with vector databases and orchestration frameworks for production use • Implemented prompt engineering plus evaluation processes for QA • Deployed and managed AI applications in Azure using containerized deployments

2024 - Present

AI Engineer (Feb 2021 – Mar 2024), Santoli Connected Network

Prompt + Response Writing (SFT)Entity (NER) Classification

Built Retrieval Augmented Generation (RAG) pipelines for semantic search by integrating vector databases and LLM orchestration into production systems. Implemented prompt engineering strategies and LLM application development, then monitored model performance and iteratively refined behavior over time. Worked on AI model inference and orchestration services exposed via APIs for downstream application use. • Developed RAG using Pinecone and Weaviate for embedding/vector storage • Designed prompt engineering approaches for intelligent features • Containerized services with Docker and deployed to Azure Kubernetes Service • Built RESTful APIs and microservices for inference/orchestration workflows

2021 - 2024

Software Engineer (Dec 2018 – Jan 2021), Hubbers Remote

Data Collection

Integrated machine learning models into production applications for predictive analytics and supported data persistence and retrieval operations through relational and non-relational databases. Developed backend services and RESTful APIs that enabled ML features to be consumed by web applications. Supported code quality by writing unit tests and maintaining reliable backend behavior. • Connected ML model outputs to production predictive analytics workflows • Worked with SQL and NoSQL databases for data storage/retrieval • Built RESTful backend services to support ML-enabled web applications • Wrote unit tests using xUnit and Moq to prevent regressions

2018 - 2021

Education

Work History