My background is primarily in backend and infrastructure engineering, with recent focus on AI systems. I have built RAG and document-ingestion pipelines, worked with embeddings, vector search, retrieval workflows, and LLM integrations, while also designing the surrounding infrastructure required to operate these systems reliably.
Professionally, I have architected and shipped production backend systems involving async processing, queues, Redis, PostgreSQL, AWS, CI/CD, observability, and distributed services. This foundation helps me approach AI systems from a production-first perspective, focusing not only on model quality but also on scalability, latency, reliability, and cost.
I actively build AI projects outside of work and continuously deepen my understanding of retrieval systems, orchestration frameworks, inference trade-offs, and agent-based architectures.
No skills.
No languages.
No employment history.
No education history.