AI Solutions Engineer focused on building real-world AI systems, agentic workflows, and developer-facing AI products. My work sits at the intersection of LLMs, product thinking, and business impact, with a strong bias toward shipping fast and iterating in production environments rather than staying in research mode.
I come from an economics background (Magna Cum Laude, Ariel University), which still influences how I design systems—thinking in terms of incentives, efficiency, and user behavior. Currently pursuing an MSc in Industrial Engineering (Data Science), where I focus on recommendation systems, multimodal data, and applied machine learning.
Most of what I do today revolves around building AI-native products, experimenting with multi-agent systems, and integrating cutting-edge models into usable workflows.
- Building agentic systems and multi-agent workflows (tools, memory, orchestration)
- Designing AI products end-to-end (from idea → prototype → production)
- Working with LLM ecosystems and evaluating new models (OpenAI, Anthropic, Google, open-source)
- Applying multimodal approaches (text, images, behavior) to recommendation systems
- Bridging research concepts with practical implementations
- Languages: Python, TypeScript, Swift
- Data & ML: Pandas, NumPy, Scikit-learn, feature engineering, recommendation systems
- LLM & AI stack: LangChain-style patterns, LiteLLM, Langfuse, LangSmith
- Agent systems: tool usage, memory design, multi-agent orchestration
- Infra & tools: n8n, Vercel, APIs, workflow automation
- Experimentation with open-source and frontier models (vLLM, Hugging Face ecosystem)
- Strong foundation in economic modeling and system thinking
- Focus on aligning AI systems with real business value
- Experience translating ambiguous problems into structured, solvable systems
- Product-oriented mindset with emphasis on usability and iteration speed
- LinkedIn: https://www.linkedin.com/in/buzagloidan/
- Website: https://buzagloidan.com/
- Email: buzagloidan@gmail.com