Bijaya Kumar Pariyar
Architecting secure, deterministic AI pipelines for commercial fintech. Bridging the gap between RAG experimentation and enterprise-scale reliability.
Visualizing RAG orchestration layers and vector retrieval paths.
Each section has its own dedicated page. Dive into whatever interests you.
I build production AI systems: retrieval pipelines, LLM orchestration, and the engineering that makes them dependable enough to sit behind a regulated decision.
On a Data Scientist internship at a US commercial real estate fintech I built the core of an AI underwriting platform: RAG document intelligence over 20+ financial document types, multi-provider LLM orchestration with fallback chains, and a deterministic credit engine that keeps the model out of the decision itself. I also maintain edaprep, an open-source preprocessing library on PyPI with contributors of its own, on a foundation of 20+ end-to-end machine learning projects.
Read my full storyThe kind of systems I design, ship, and own end to end
Provider fallback chains across AWS Bedrock, Gemini & OpenAI with circuit breakers and graceful degradation.
pgvector HNSW search, Titan/sentence-transformer embeddings, and CrossEncoder reranking over real documents.
Rule-based credit risk scoring with zero LLM in the critical path: auditable, explainable, and reproducible.
FastAPI + async job workers on AWS ECS Fargate, shipped via GitHub Actions CI/CD with layered security.
A snapshot of my GitHub activity
github: @bijay-odyssey / visibility: public