Tell me what you’re trying to build.

Bring a specific problem, or describe the frontier workflow you want to unlock. I’ll map the multi-agent system, RAG/data pipeline, automation layer, product design and DevOps path to ship it.

Pedro Antonelli — frontier AI Engineer focused on senior-level multi-agent systems, dreaming loops, RAG, automations, data engineering and end-to-end AI products.

Operating model

Systems-first AI engineering, from brief to production.

The portfolio is built around frontier AI work: senior multi-agent orchestration, dreaming/simulation loops, RAG and data pipelines, agentic automations, product interfaces and production operations that can be inspected directly. The leverage comes from a swarm of agents that researches, codes, reviews and ships in parallel, so a single AI Engineer can move with the cadence of a compact studio.

See the method
Design is not decorationA model is only useful if a human can actually use it. I obsess over the experience as much as the architecture.
Grounded over confidentI’d rather a system say “I don’t know” than hallucinate. Retrieval, citations and evals keep it honest.
Ship, then observeProduction teaches what demos can’t. I deploy early, measure everything and iterate on real signal.
Leverage through agentsMy swarm does the parallel grunt work so I can stay on the judgment calls that actually need a human.

What I do

Five ways I turn frontier AI into shipped systems

From senior-level multi-agent systems and dreaming loops to full multi-cloud products — AI engineering first, with data engineering, design and ops under one roof.

Frontier Multi-Agent Systems

Senior-level orchestration for agents that plan, dream, act and self-review.

I work at a senior level in multi-agent architecture: orchestrators, specialist sub-agents, tools, memory, state, evals, dreaming/simulation loops and auditable decision logic. Not a chatbot — a frontier AI system that does the work.

  • Orchestrator + specialized sub-agents (LangGraph)
  • Tool calling, memory and state management
  • Dreaming/simulation loops, self-review and evals
  • Parallel execution tuned for cost and latency

RAG & Data Engineering

Pipelines that make your data usable for AI.

Retrieval and data pipelines that turn messy sources into trustworthy AI systems: ingestion, modeling, chunking, embeddings, hybrid search, re-ranking and citations — so the model stops guessing.

  • Ingestion, modeling and quality checks
  • Chunking + embedding pipelines
  • Hybrid (vector + keyword) retrieval & re-ranking
  • Cited, grounded answers with eval harness
  • Vector DB and Postgres setup (pgvector, Pinecone, Qdrant)

Multi-Cloud & DevOps

Shipped, scaled and observable.

I deploy and operate AI workloads across GCP, AWS and Azure: containers, serverless, CI/CD, infra-as-code and observability. The system runs reliably and you can see exactly what it’s doing.

  • Containerized deploys (Docker, Cloud Run, ECS, AKS)
  • CI/CD pipelines and infra-as-code
  • Secrets, cost guards and rate limiting
  • Logging, tracing and alerting for LLM apps

Frontier Automations & Skills

Agentic workflows that replace manual drag with self-running systems.

I turn repetitive operations into frontier automations: event-driven workflows, agentic skills, tool-calling systems, triggers, monitors and escalation paths that plug into the tools you already use.

  • Reproducible, versioned agentic skills
  • Scheduled & event-driven automations
  • Integrations with tools, APIs, monitors and alerts
  • Docs and handoff so it lives in your stack

Full AI Product Design & Build

The whole thing — UX, code and the AI inside.

When you need the complete product: I design the interface, build the full-stack app and embed the AI so it feels like one coherent thing. Design taste and engineering depth from the same person.

  • Product & UX design (Figma → shipped)
  • Full-stack build (Next.js, TypeScript, APIs)
  • AI features embedded natively in the UX
  • From prototype to deployed, polished product
See all services

Selected work

Systems, agents and products I’ve built

A selection of frontier AI systems I designed and engineered end-to-end — from RAG knowledge engines to autonomous agent swarms, simulations and automations.

Agent Swarm

Personal Agent Swarm

My own frontier agent system: an orchestrator delegates research, coding, review, publishing and dreaming/simulation loops to specialized sub-agents running in parallel. It’s how I ship like a studio of one.

LangGraphOpenCLAWHermesPython
In production
RAG System

RAG Knowledge Engine

A retrieval engine over large, messy document sets. Hybrid search and re-ranking return grounded, cited answers — with an eval harness that catches regressions before they ship.

LangChainpgvectorCohere RerankFastAPI
Live
Automation

Inbox Spend Tracker

An agent that scans an inbox daily, detects every purchase and recurring charge, normalizes currency and pushes spending into a personal dashboard. Read-only, zero spreadsheets.

Gmail APIClaude APICronNext.js
Live
See all projects

By the numbers

A track record, not just a title

0AI systems shipped
0Clouds in production
0Agents in my swarm
0Years designing & building

Let’s build

Have an idea that needs AI to actually work?

Tell me what frontier workflow you want to build. I’ll bring multi-agent architecture, automations, data pipelines, product design, DevOps and a swarm of agents to ship it.

Start a conversationEmail me directly