9 production-grade AI systems spanning the full applied AI stack.
I built a pipeline that generates synthetic training data, validates it with an LLM judge, and self-corrects until every record passes. Started with a 20% failure rate, ended at zero.
I tested 16 RAG configurations and found that semantic chunking + OpenAI embeddings + Cohere reranking gets 0.747 Recall@5 on structured Markdown docs. This is how I got there.
I fine-tuned all-MiniLM-L6-v2 on 1,475 dating profile pairs and flipped Spearman from -0.22 to +0.85. LoRA got 96.9% of that using 0.32% of the parameters.
I generated 250 synthetic resumes across 5 fit levels, labeled them for 5 failure modes with zero LLM calls, and found that writing template choice accounts for a 66-percentage-point difference in failure rates (chi-squared=32.74, p<0.001).
I built a RAG system from scratch with no LangChain, tested 46 configurations across 5 chunking strategies, 4 embedding models, and 3 retrieval methods, and found that heading-aware chunking + OpenAI embeddings hits NDCG@5 = 0.896 and Recall@5 = 1.0.
Multi-agent system that learns your writing style from samples and generates content that sounds like you. CrewAI agents handle style analysis, content planning, and draft generation.
Multi-agent system that helps Product Managers go from raw customer feedback to prioritized roadmap gaps. CrewAI agents handle sentiment scoring, theme extraction, roadmap alignment, and gap detection.
Multi-agent system that analyzes a Jira backlog, estimates effort, identifies dependencies, and proposes sprint composition. Built with CrewAI.
Multi-agent DevOps assistant that monitors CI/CD pipelines, correlates logs and metrics, diagnoses root causes, and suggests remediations with risk-based approval workflows. Built with CrewAI.