Ship LLM systems you can measure, trust, and maintain.
The demo was the easy part. The hard part is retrieval that holds up on real queries, agents that don’t wander, and evals that catch regressions before your users do. That is what we build — hands-on, in your stack, with your team — and hand off clean.
Engagements that match where you are
Every engagement ends with something your team owns — working code, an evaluation set, and a plan — not a deck.
LLM Strategy Sprint
2 weeks- The two or three use-cases worth building first, with ROI framing
- Data readiness and risk review: privacy, security, compliance
- An architecture roadmap your engineers can start on Monday
RAG / Agent MVP
4–6 weeks- A working system on your data — not a slide
- An evaluation harness and test set you own
- Deployment plan and clean handoff to your team
Production Hardening
2–4 weeks- Eval gates and regression tests, so changes stop breaking things
- Latency and cost down, with the numbers to prove it
- Guardrails for the failure modes you’ve seen — and the ones you haven’t yet
Fractional AI Lead
Monthly- Weekly architecture and code reviews
- Model and vendor decisions made on evidence, not hype
- Hiring and upskilling, so you need us less over time
Before founding Data For Science, Bruno was VP of Data Science & Finance at JPMorgan Chase, where he led ML and LLM deployments for the bank’s finance divisions. He has taught 170+ live sessions for O’Reilly since 2019, writes the Data Science Briefing (340+ weekly issues), and holds a PhD in the Physics of Complex Systems. The common thread: taking LLM, RAG, and agentic systems from prototype to something you can actually run in production.
More about Bruno →Recent hands-on write-ups from the blog — the same patterns we use in engagements: