Biruk Abza

Developed an AI-driven coding assistant for the MeTTa programming language using a RAG architecture.
Achieved 91% benchmark accuracy on a custom evaluation suite.
Reduced average response latency from 16s to 8s.
Designed a tool-augmented retrieval system for the assistant.
Deployed the AI assistant web platform on a DigitalOcean VPS.
Built an MCP server integration for Claude Code.

Contributed to Rejuve.Bio’s AI-driven platform.
Optimized genomic variant annotation workflows.
Implemented real-time task feedback using WebSocket.
Engineered a literature mining engine using PubMed API and Sentence Transformers.