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.
No pitch deck. You leave with a written scope and next steps, whether or not we work together.
What we build
-
RAG & Retrieval
Retrieval that holds up on real queries: chunking, hybrid search, reranking, and the eval set that proves it works before it ships.
-
Agents & Workflows
Agents with boundaries: tool design, planning patterns, guardrails, and explicit handling of the ways they fail.
-
Evaluation & Observability
Quality, latency, and cost you can actually see: eval harnesses, regression gates, and monitoring your team keeps using after we leave.
Bruno Gonçalves, PhD
Founder & AI Consultant
The common thread: taking LLM, RAG, and agentic systems from prototype to something you can actually run in production.
-
VP, Data Science & Finance
JPMorgan Chase
Led ML and LLM deployments for the bank’s finance divisions before founding Data For Science.
-
170+ live sessions
O’Reilly, Pearson & Packt
50+ courses on RAG, agents, evaluation, and LLMOps, taught to working engineers since 2019.
-
340+ weekly issues
Data Science Briefing
Read by 3,000+ practitioners every week since 2019.
-
PhD, Complex Systems
Former NYU Data Science Fellow
Research covered by MIT Technology Review, The Economist, Wired, and The Atlantic.
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.
| Engagement | Duration, in weeks | What your team owns at the end | Best when |
|---|---|---|---|
| LLM Strategy Sprint | 2 weeks |
| you have budget and ambition, but no agreed first step |
| RAG / Agent MVP | 4–6 weeks |
| the prototype exists and “production” is the open question |
| Production Hardening | 2–4 weeks |
| it’s live, and every change feels like a gamble |
| Fractional AI Lead | Monthly ongoing |
| you need senior judgment on tap without a full-time hire |
We work under NDA, follow your security policies, and can work entirely inside your environment when data can’t leave it.
How we work
-
Diagnose
Agree on what “working” means
Use-cases, data, security constraints, and the metrics we’ll be judged on — written down before any code.
-
Build
Ship an MVP with evals from day one
Every iteration is measured against the same test set, so improvement is a number, not an opinion.
-
Harden
Make it yours to run
Monitoring, regression gates, documentation, and training, so the system keeps working after we step back.
Handoff
Your team owns the code, the evaluation set, and the plan.
We publish the code, not just the advice.
Recent hands-on write-ups from the blog — the same patterns we use in engagements:
- Weekly, in your inbox: the Data Science Briefing
- Code: github.com/DataForScience
AI Engineering Cookbook
Coming 2027 from Pearson. 18 hands-on recipes for production AI systems.
Ready to scope a project?
Thirty minutes. We’ll pin down the problem, the success metric, and the shortest path to a working system — and send you the notes.
Or email info@data4sci.com