Distributed Systems & Applied GenAI Deep-Dive

Building or interviewing on something at real scale — a Kafka-based event pipeline, a multi-agent AI system, a RAG pipeline that needs to actually hold up in production? This is a working session on your real system, not a generic architecture lecture.

Only for engineers working on or interviewing for distributed backend systems or applied GenAI/agentic systems — pick your track when you book.

In this session:

1. A deep dive into your specific architecture — event-driven design, Kafka/Redis/Postgres patterns, exactly-once delivery, idempotency, sharding — or multi-agent orchestration, RAG design, eval strategy, and LLM cost optimization
2. Real production patterns pulled from systems I've built processing 10M+ events/day and 25M+ ad views/day
3. Specific, concrete fixes for your actual system — not textbook theory
4. Direct feedback on what would actually break at scale, and why

Why me: At Coinbase I led the team that built a LangGraph multi-agent platform processing 10M+ GitHub events/day across 850+ repos — that system cut LLM inference costs 70% (~$680K/year), with testing built on golden-dataset regression and LLM-as-judge evaluation. Before that, 5 years at Media.net building high-throughput ad-fraud systems (25M+ ad views/day, Kafka + Spark). This is production experience, not a weekend project.

Book below — most "AI mentors" haven't shipped a multi-agent system that cut real, measured costs. I have.