Engineering Manager · Applied AI · Cloud The next decade belongs to engineering leaders who build with AI.
I spent the last two decades leading engineering teams at State Street, Centene, and EY. Building products that handle real money, real patient data, and real regulatory scrutiny. The kind of work where downtime means someone's claim doesn't get processed and a bad deployment means financial loss.
Now I am applying that same engineering discipline to AI. I am building 9 AI systems covering RAG pipelines, embedding fine-tuning, and multi-agent orchestration. Each one has evaluation frameworks, architecture decision records, and metrics I would trust in a code review. The same standards I would hold any production system to.
Leadership
Technical
What I'm building
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 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.
How Instructor, flat schemas, and two-phase validation got me to 100% structured output success across 580 LLM-generated records.
10 min read
What to do when your team was promised promotions or headcount that never materialized, and you're the new manager holding the bag.
6 min read
How to fix invisible attribution in distributed teams, and why credit theft is the most corrosive trust pattern a manager can inherit.
6 min read
More about my background