I’m an Applied AI Engineer focused on building production-grade LLM systems that go beyond prototypes and demos.
My work centers on designing end-to-end AI pipelines that combine Retrieval-Augmented Generation (RAG), vector databases, automated evaluation, and MLOps practices such as experiment tracking and model governance. I enjoy solving the systems problems around AI — orchestration, reliability, deployment decisions, and failure handling — that determine whether models actually work in real-world applications.
I’m particularly interested in building AI systems that are scalable, observable, and safe to deploy, and in bridging the gap between model experimentation and dependable production systems with real business impact.
- LLM-powered systems with Retrieval-Augmented Generation (RAG)
- Semantic search platforms using vector databases
- Automated ML pipelines with evaluation and promotion logic
- Production-style AI systems with orchestration, monitoring, and governance
- Backend services that integrate AI capabilities into real applications
- Designing AI systems that can be trusted in production
- Bridging the gap between backend engineering and applied AI
- Building pipelines that are observable, reproducible, and safe
- Learning by building real systems, not just reading theory
- Advanced RAG evaluation techniques
- Agentic AI systems (production-oriented)
- Scalable MLOps architectures
- Cloud-native deployment patterns for AI systems
Always open to discussions, collaborations, and opportunities in Applied AI & ML Engineering.