Prompt Engineer & LLM Behavior Engineer
I build reliable LLM workflows: prompt systems, evaluation pipelines, and agent automation for real-world tasks.
Background in ML data quality and LLM evaluation; I treat prompts as measurable systems.
- Open to roles: Prompt Engineer, LLM Behavior Engineer, AI Automation Engineer
- Contact: kazkozdev@gmail.com
- LinkedIn: Artem KK
- prompt-engineering-studio — local-first workspace for prompt design and evals with 70+ prompting techniques.
- system-prompt-benchmark — security testing across 287+ attack vectors (injection, jailbreaks, leakage).
- dspy-optimization-patterns — teacher-student optimization patterns for quality/cost trade-offs (**up to 50x cost reduction).
- dataset-creator — synthetic dataset generation for distillation and prompt/eval workflows.
- NovelGenerator — autonomous multi-agent fiction pipeline (86 stars).
- browser-agent-chrome-extension — Claude-like Chrome browser agent focused on cost-efficient automation.
- llmflow-search — deep research agent that synthesizes reports from multiple web sources.
- vision-agent-analyst — multimodal analysis for charts, UI screenshots, and PDFs.
- llm-evaluation-framework — A/B testing, benchmarking, LLM-as-a-judge, regression tracking.
- production-rag — multi-strategy retrieval, hybrid search, and evaluation support.
Python TypeScript DSPy LangChain LangGraph RAG Prompt Engineering LLM Evals Agentic Workflows