AI/LLM Engineer specializing in agent systems, memory architectures, and context engineering.
Actively seeking roles in AI Engineering / LLM Applications / Agent Workflows.
- Build LLM-based agents, tool-use frameworks, long-term memory systems
- Experience with prompt engineering, context engineering, RAG pipelines, and model inference
- Interested in AI automation, workflow orchestration, and multi-agent collaboration
- Hands-on with LLM-backed decision-making and sequential reasoning
- Passionate about making LLM reasoning more reliable, structured, and deployable
- Language: Python, C, C++, HTML, CSS, JS
- LLM/Agent: ReAct, Reflexion, Memory-Augmented Agents
- Model stack: vllm, ollama, HuggingFace
- Backend: Vector DB, Docker, Linux, git
- Research: RAG pipelines, Sequential decision-making with LLM, Prompt & context optimization strategies