AI Agent Developer & Prompt Engineer.
Autonomous AI systems — agents, LLM apps, prompt optimization.
Background in ML data quality & LLM evaluation.
Autonomous systems capable of complex reasoning and execution
- NovelGenerator — Fiction generator using multi-agent swarm to create complete novels with coherent plots
- LLMFlow Agent — GAME-based framework for building autonomous AI agents
- LLMFlow Search — Deep research agent that synthesizes reports from multiple web sources
- Vision Agent Analyst — Multimodal agent analyzing charts, UI screenshots, and PDFs for reporting
- dev-ops-agent — Technical agent performing code reviews and automated bug-fixing proposals
Interface between human intent and LLM output
- Prompt Engineering Studio — Transforms basic inquiries into research-backed prompts optimized for performance metrics
- System Prompt Benchmark — Security testing against 287+ attack vectors (jailbreaks, injections)
- Synthetic Data Foundry — Generating high-quality datasets for model distillation
- dspy-optimization-patterns — Programmatic optimization using DSPy
- Production Rag — Multi-strategy retrieval, hybrid search, and comprehensive evaluation framework
- llm-evaluation-framework — A/B testing pipeline, benchmarking, and LLM-as-a-judge implementation