Key Skills

Software

No software listed

Top Subject Matter

Enterprise IT – ITSM Integration & Secure Authentication

Education Technology – Academic Scheduling & AI Routing

Software Engineering – LLM Output Evaluation & QA Automation

Top Data Types

Text

Top Task Types

Computer Programming/Coding

RLHF

Fine-tuning

Red Teaming

Function Calling

Evaluation/Rating

Text Generation

Question Answering

Freelancer Overview

As an Applied AI Engineer, I specialize in the rigorous evaluation, routing, and integration of LLM outputs for enterprise production systems. My core expertise lies in context engineering, model behavior assessment, and output quality control. I have directly engineered automated LLM-driven QA workflows to audit massive, 30,000-line architecture pull requests for security vulnerabilities and state-management edge cases. Furthermore, I actively evaluate model performance using qualitative reviews, latency measurements, and task success rates derived from live production traffic. My technical foundation spans backend infrastructure and low-level performance, including Python, FastAPI, TypeScript, and CUDA C. Because I build retrieval-augmented generation (RAG) pipelines and enforce multi-tenant data isolation, I possess a deep understanding of how models process complex context windows. This combination of hands-on architectural experience and direct model evaluation allows me to generate highly accurate training data, establish strict guardrails, and meticulously assess AI reasoning for complex software engineering tasks.

Labeling Experience

Education

Work History