I am a Computer Science and Engineering undergraduate and AI engineer focused on building retrieval-augmented generation (RAG) and document AI systems. I work primarily with Python, FastAPI, large language models, retrieval pipelines, and backend services.
I have built RAG applications using hybrid search, reranking, citations, OCR, and evaluation workflows. My work includes improving retrieval quality and latency through dense retrieval, BM25, pgvector HNSW, and cross-encoder reranking.
I have experience developing reliable AI infrastructure, including an OpenAI-compatible LLM gateway with rate limits, retries, provider failover, circuit breakers, streaming, tracing, and operational dashboards. I use Redis, PostgreSQL, OpenTelemetry, Prometheus, Grafana, and Docker in these systems.
During my AI Engineering internship, I built a Siemens Opcenter RAG assistant for manufacturing documents. I also developed document ingestion pipelines using PDF parsing and OCR tools and measured system performance through local benchmarks.
I enjoy solving algorithmic problems and have solved more than 1,000 problems across LeetCode and GeeksforGeeks. I have also mentored students in C programming and contributed to undergraduate research on influence maximization in social networks.
I am seeking opportunities where I can contribute to applied AI, LLM engineering, RAG systems, backend development, and document intelligence products.
