Professional Overview
I build measurable prompt systems. Through personal projects I created a prompt evaluation framework that improved accuracy, a local RAG assistant with source grounding and anti-hallucination controls, and system prompts that reduce hallucinations. Focused on evaluation. Open to remote junior roles.
Experience
AI Expertise
Skills
Employment Type
Description of Responsibilities
- Built prompt evaluation framework with regression detection
- Designed system prompts to reduce LLM hallucinations
- Developed local RAG assistant with source citations
- Created automated tests for accuracy and abstention
- Evaluated prompts across Llama, Qwen and DeepSeek models
Key Achievements / KPIs
- Improved prompt accuracy from 60% to 90%
- Achieved refusal on unanswerable questions
- Built fully local RAG system that avoids hallucinations
- Benchmarked 4 prompt versions on 3 different models
Education
Field of Study: Computer Science
Areas of Expertise
NLP & Prompt Engineering
Build natural language processing systems, fine-tune large language models, and craft reliable production prompts for AI-powered products.
