I build scalable AI systems using RAG pipelines, vector search systems, and LLM-driven workflows.
Applied AI Backend Engineer with ~2 years of experience building RAG pipelines, vector search systems, and LLM-driven workflows using Python and FastAPI. Experienced in designing scalable AI services, retrieval-augmented generation (RAG) systems, hybrid search pipelines, and secure production APIs.
Built a context retrieval pipeline and APIs that ingest documents into MongoDB, chunk them, create embeddings, and index them in Qdrant for semantic search. Implemented metadata and provenance so every retrieved chunk is traceable.
AI Urban Planning Assistant. Built an AI pipeline to process construction drawings and documents into structured data. Implemented LLM-based extraction for rooms, floors, and equipment schedules.
Orchestrated AI-driven audio and avatar generation pipelines integrating LLM-based script processing, ElevenLabs TTS, and external media services with asynchronous background job processing.
Optimized leaderboard and tournament APIs using MongoDB aggregation, compound indexing, caching, and pagination. Implemented background score computation and atomic database operations.
Interested in my detailed professional background? Download my latest resume here.
Download ResumeI'm currently looking for new opportunities in AI Backend Engineering. Whether you have a question or just want to say hi, my inbox is always open!