Engineering Specialization & Core Pillars
I build, evaluate, and optimize autonomous LLM agent systems with an emphasis on context engineering, local hybrid retrieval (RAG), and empirical LLM safety research. My work bridges low-level systems programming in Rust and C++ with high-throughput neural pipelines in PyTorch and transformers.
- Context Engineering & Agent Harnesses: Explicit token admission, context inspection, memory compaction, and session continuity for autonomous coding assistants.
- High-Throughput Local Retrieval: Merging Tantivy BM25 lexical indexing with LanceDB columnar vector storage via Reciprocal Rank Fusion for air-gapped search.
- LLM Safety & Red-Teaming: Controlled evaluations of prompt injection, role confusion, chain-of-thought forgery, and reasoning-channel leakage.
Selected Projects & Applied Research
- Elpis
An agent harness built on Codex, with a desktop app and a terminal app, where you choose what each agent sees.
- rag-mcp
An MCP server that finds relevant passages in local files and code without loading the whole workspace.
- LLM Safety
LLM safety research on tool-result ordering, framing and reasoning leakage, and agent hierarchies.
- Financial Market Analysis
EUR/USD research comparing a dual-tower Transformer with tree models in backtests.
- WhisperType
Local dictation for Linux/NVIDIA: speak, transcribe, and paste directly into the active app.