Presentation
Recently, I've expanded into AI/LLM engineering — building Retrieval-Augmented Generation (RAG) pipelines, integrating LLM APIs (OpenAI, Claude) into backend systems, and working with vector embeddings and LangChain4j to add intelligent features to existing applications. I bring a production-engineering mindset to AI work: not just prototyping a chatbot, but building it to scale, handle failure gracefully, and integrate cleanly with your existing stack.
What I bring to a project:
5+ years designing and shipping microservices in Java/Spring Boot, with hands-on work in banking/fintech (payments, trade finance, virtual account management) and geospatial data pipelines (AWS EMR, Kafka, Redis)
Practical experience building RAG systems, LLM API integrations, and prompt-engineered workflows
Strong focus on system reliability, clean API design, and production-readiness — not just "it works on my machine"
Clear communication and reliable delivery — I scope carefully, flag risks early, and keep you updated
Whether you need a robust backend service, an LLM feature bolted onto an existing product, or someone who can do both, I'd love to help.

