← All projects
2024-presentActive

LLM Research Assistant Platform

A full-stack assistant for retrieval, question answering, and research knowledge automation using hybrid search, reranking, and agentic workflows.

Role
Research Assistant and AI Engineer
Context
Office of Strategic Initiatives, University at Albany
Focus
LLM, RAG, Reranking, Agents, Evaluation

Problem

Institutional research teams need dependable access to large, heterogeneous knowledge collections without relying on ungrounded model responses.

Context

The current site describes this work as a full-stack LLM assistant for retrieval, question answering, and knowledge automation.

My role

Led development of retrieval, reranking, agentic workflow, and evaluation components.

Constraints

Architecture

The source material identifies hybrid retrieval, metadata indexing, cross-encoder reranking, task decomposition, memory modules, orchestration, and automated evaluation.

TODO_REVIEW: Add an approved architecture diagram and exact component stack.

Technical decisions

Trade-offs

TODO_REVIEW: Document latency, retrieval depth, model selection, hosting, and cost trade-offs.

Results

TODO_REVIEW: Add verified qualitative outcomes, benchmark definitions, and approved metrics. No result numbers were available in the source repository.

Screenshots

TODO_REVIEW: Add approved product screenshots or a redacted demo.

TODO_REVIEW: Add public code, demo, article, or institutional links where permitted.