Projects

TerrierGrader

Academic AI

Production evaluation pipeline with rubric-aligned generative assessment and self-consistency verification. Retrieval-augmented feedback synthesis across configurable assessment criteria. 500+ documents per evaluation cycle, 3 institutional deployments, 60% overhead reduction.

You'll learn: RAG Systems · Prompt Engineering · NLP · FastAPI

View project →

Supply Chain Optimizer

Optimization AI

Hierarchical multi-agent system with domain-constrained specialist delegation for cross-vertical optimization. Orchestrator-mediated coordination across regulatory compliance, demand forecasting, and inventory agents.

You'll learn: Agent Architecture · Ensemble ML · XGBoost · Statistical Validation

View project →

Multi-agent clinical evidence retrieval — supervisor-routed specialists, hybrid search, and citation-grounded synthesis.

You'll learn: Multi-Agent RAG · Hybrid Vector Search · LLM Reranking · Citation Systems

View project →

BizSight

Business AI

multi-agent orchestration layer on AWS with Model Context Protocol integration and dynamic tool selection. Function-calling coordination across domain-specialized agents. Deployed across 4 geographic regions at 90% cost reduction.

You'll learn: AWS · MCP Protocol · Agent Orchestration · Function Calling

View project →

Swaad

Recommendation AI

Agentic RAG pipeline with self-reflective retrieval and multi-dimensional embedding space for preference modeling. Unstructured document ingestion via OCR with domain-specific entity extraction.

You'll learn: Agentic RAG · Vector Databases · Pinecone · Embedding Models

View project →

Gusto

Graph AI

Heterogeneous graph neural network for preference-aware entity matching. GNN message-passing over multi-relational interaction graphs with hybrid ranking. Cold-start mitigation across sparse interaction regimes.

You'll learn: Graph Neural Networks · PyTorch Geometric · Recommendation Systems · Collaborative Filtering

View project →

Sector Rotation System

Ensemble AI

9-agent ensemble system with LSTM, CNN, and RNN specialists. 25-year temporal validation with statistical significance testing, Sharpe ratio analysis, and ablation studies.

You'll learn: LSTM · CNN · RNN · Ensemble Learning

View project →