{"$schema":"https://raw.githubusercontent.com/jsonresume/resume-schema/v1.0.0/schema.json","basics":{"name":"Alejandro Zanello","label":"AI Engineer — Agent Runtimes, Multi-Agent Systems & GenAI","email":"me@azanello.com","phone":"+54 9 351 214 1761","url":"https://azanello.com","summary":"AI Engineer with 6+ years shipping production software across mobile, backend, and web, now focused on agent runtimes and multi-agent systems. Author of Akashi, an open-source agent framework published on pub.dev as a 14-package monorepo: a streaming tool-calling runtime, token-accurate context management, multi-provider failover by error type, durable checkpoint/resume with human-in-the-loop, OpenTelemetry tracing, and structured-output self-repair to contain non-deterministic model behaviour. Builds LLM systems with LangChain, LangGraph, RAG, and the Model Context Protocol (MCP) in TypeScript and Python. Certified: IBM Generative AI Engineering Professional Certificate, Agentic AI Engineering Specialization and AWS Certified Cloud Practitioner.","location":{"city":"Córdoba","region":"Córdoba","countryCode":"AR"},"profiles":[{"network":"LinkedIn","username":"alejandrozanello","url":"https://linkedin.com/in/alejandrozanello"},{"network":"GitHub","username":"AleSZanello","url":"https://github.com/AleSZanello"},{"network":"Credly","username":"azanello","url":"https://www.credly.com/users/azanello"}]},"work":[{"name":"Freelance","position":"Independent AI & Full-Stack Engineer","location":"Remote","startDate":"2025-06","highlights":["Multi-tenant conversational AI agents in a TypeScript monorepo: Hono gateway, LangGraph.js with Postgres checkpointing, an MCP server, Langfuse/OpenTelemetry tracing, and automated evals.","Real-time, event-driven data systems in Python (asyncio, FastAPI, WebSockets) with a Rust low-latency component, ingestion and backtesting pipelines (DuckDB, PyArrow), and containerized deployments.","6+ white-label Flutter apps shipped from shared codebases: multi-flavor builds, Bloc/Riverpod, RevenueCat subscriptions, Firebase and Supabase, CI/CD with Codemagic and fastlane.","Next.js + Supabase products for small businesses: row-level security, Edge Functions, MercadoPago payments with webhooks, PWAs, PDF/Excel reporting, and ETL jobs."]},{"name":"Somnio Software","position":"FlutterFlow Developer","location":"Remote","startDate":"2024-10","highlights":["Software engineering on internal tooling and platform work, using Python, TypeScript and Dart.","AI-assisted, spec-driven development practices within a product engineering team.","Contributor to the open-source Somnio AI Tools CLI.","Core contributor to FlutterFlow’s public issue triage (600+ issues)."]},{"name":"Detecta","position":"Software Engineer","location":"Mexico (Remote)","startDate":"2023-07","endDate":"2024-10","highlights":["Built and shipped the Detecta Security Platform, a triple-platform product serving internal operations, customers, and field drivers.","Integrated real-time GPS fleet tracking via Wialon, backed by Firebase and AWS microservices built with NestJS."]},{"name":"Detecta","position":"LowCode Specialist","location":"Mexico (Remote)","startDate":"2022-08","endDate":"2023-07","highlights":["Delivered production mobile applications with FlutterFlow and Flutter on a Firebase backend."]},{"name":"California Fitness","position":"IT Manager","location":"Cancún, Mexico","startDate":"2017-10","endDate":"2021-11","highlights":["Built and maintained a fully custom web CRM in PHP/MySQL, shipping weekly improvements across all branches.","Introduced QA automation with Selenium and Cypress covering the CRM and mobile applications.","Replaced manual business processes with automated workflows; maintained and optimized the production database.","Managed the external ERP integration project with the vendor, and ran eCommerce and online client support."]},{"name":"California Fitness","position":"Branch Office Manager","location":"Cancún, Mexico","startDate":"2016-01","endDate":"2017-10","highlights":["Managed branch operations, staff training, inventory, and provider relationships before moving into the IT organization."]}],"education":[{"institution":"Universidad Interamericana para el Desarrollo","area":"Engineering, Systems Engineering","startDate":"2014","endDate":"2017"},{"institution":"Deusto Formación","area":"Diploma, Mobile Application Development","startDate":"2015","endDate":"2015"},{"institution":"Universidad Tecmilenio","area":"Bachelor's, International Business","startDate":"2011","endDate":"2013"}],"certificates":[{"name":"IBM Generative AI Engineering Professional Certificate","date":"2026-10-17","issuer":"IBM via Coursera","url":"https://www.coursera.org/account/accomplishments/specialization/DT7I0XVP5JQZ"},{"name":"Agentic AI Engineering Specialization","date":"2026-05-22","issuer":"Edureka via Coursera","url":"https://www.coursera.org/account/accomplishments/specialization/V20XQMM270EL"},{"name":"AWS Certified Cloud Practitioner","date":"2024-05-03","issuer":"Amazon Web Services","url":"https://www.credly.com/badges/a1c0c051-7d10-4633-86bb-7d9949b01615"},{"name":"AI Agents Using RAG and LangChain","date":"2026-10-17","issuer":"IBM via Coursera — part of IBM Generative AI Engineering Professional Certificate","url":"https://www.credly.com/badges/97306a60-b4c6-4fa0-a61f-6fe39a32e176"},{"name":"Generative AI Applications Specialist","date":"2026-10-17","issuer":"IBM via Coursera — part of IBM Generative AI Engineering Professional Certificate","url":"https://www.credly.com/badges/f6ca33c9-0110-4e74-89a6-c36728d445bc"},{"name":"Generative AI Advanced Fine-Tuning for LLMs","date":"2026-10-16","issuer":"IBM via Coursera — part of IBM Generative AI Engineering Professional Certificate","url":"https://www.credly.com/badges/b0c909a3-9559-477f-9bc2-50a4fa40145a"},{"name":"Generative AI Engineering with Transformers & LLMs","date":"2026-10-13","issuer":"IBM via Coursera — part of IBM Generative AI Engineering Professional Certificate","url":"https://www.credly.com/badges/96badce6-3d3c-45ea-b162-d5c1092e030b"},{"name":"Deep Learning Essentials with Keras","date":"2026-10-06","issuer":"IBM via Coursera — part of IBM Generative AI Engineering Professional Certificate","url":"https://www.credly.com/badges/138f7811-c12d-4221-a435-2c3cd2ffaf94"},{"name":"Generative AI and LLMs: Architecture and Data Preparation","date":"2026-10-06","issuer":"IBM via Coursera — part of IBM Generative AI Engineering Professional Certificate","url":"https://www.credly.com/badges/f8191566-1df1-4c39-a4fb-40a1e7453399"},{"name":"Generative AI Foundational Models for NLP & Language Understanding","date":"2026-10-06","issuer":"IBM via Coursera — part of IBM Generative AI Engineering Professional Certificate","url":"https://www.credly.com/badges/d9134bd0-ed3b-49ff-a2a0-922f955ccac4"},{"name":"Generative AI Language Modeling with Transformers","date":"2026-10-06","issuer":"IBM via Coursera — part of IBM Generative AI Engineering Professional Certificate","url":"https://www.credly.com/badges/d100c180-6965-44c9-bcb9-d38e34708313"},{"name":"Data Analysis with Python","date":"2026-10-05","issuer":"IBM via Coursera — part of IBM Generative AI Engineering Professional Certificate","url":"https://www.credly.com/badges/aeba365e-8f08-4a16-b19c-e1bb684b83f6"},{"name":"Machine Learning with Python (V2)","date":"2026-10-05","issuer":"IBM via Coursera — part of IBM Generative AI Engineering Professional Certificate","url":"https://www.credly.com/badges/955ce890-b565-4943-82c3-1c7ea8531154"},{"name":"Python Project for AI and Application Development","date":"2026-06-05","issuer":"IBM via Coursera — part of IBM Generative AI Engineering Professional Certificate","url":"https://www.credly.com/badges/3e65ebc3-41b1-4d7c-92fd-43a73e6089a7"},{"name":"Building Generative AI-Powered Applications with Python","date":"2026-06-03","issuer":"IBM via Coursera — part of IBM Generative AI Engineering Professional Certificate","url":"https://www.credly.com/badges/9a382908-73ab-4584-a26a-648f2f8d8ff1"},{"name":"Artificial Intelligence Essentials V2","date":"2026-06-01","issuer":"IBM via Coursera — part of IBM Generative AI Engineering Professional Certificate","url":"https://www.credly.com/badges/a05a8a27-a38b-4988-bc00-4255206357f3"},{"name":"Generative AI Essentials","date":"2026-06-01","issuer":"IBM via Coursera — part of IBM Generative AI Engineering Professional Certificate","url":"https://www.credly.com/badges/333b935e-5eb8-4708-8b25-293d69d1594a"},{"name":"Generative AI: Prompt Engineering","date":"2026-06-01","issuer":"IBM via Coursera — part of IBM Generative AI Engineering Professional Certificate","url":"https://www.credly.com/badges/dc139939-0e30-4c27-8d47-299a7b2154d4"},{"name":"Developing MCP-Powered Agentic AI Systems","date":"2026-05-22","issuer":"Edureka via Coursera — part of Agentic AI Engineering Specialization","url":"https://www.coursera.org/account/accomplishments/verify/AXFAZWOU3U40"},{"name":"Multi-Agent Systems with LangGraph","date":"2026-05-21","issuer":"Edureka via Coursera — part of Agentic AI Engineering Specialization","url":"https://www.coursera.org/account/accomplishments/verify/POMUZ7UGQNBS"},{"name":"Applied Agentic AI Pipelines with LangChain","date":"2026-05-20","issuer":"Edureka via Coursera — part of Agentic AI Engineering Specialization","url":"https://www.coursera.org/account/accomplishments/verify/10KPCYZ9UVW9"},{"name":"Building Your First AI Agent with LangChain","date":"2026-05-18","issuer":"Edureka via Coursera — part of Agentic AI Engineering Specialization","url":"https://www.coursera.org/account/accomplishments/verify/12NAU4R4NZEB"}],"skills":[{"name":"AI & Agentic","keywords":["LangChain","LangGraph","LangSmith","MCP","RAG","Evals","Langfuse","pgvector","Anthropic SDK","OpenAI","Google Gemini","Vercel AI SDK","Claude Code","Cursor","Windsurf","GitHub Copilot"]},{"name":"Languages","keywords":["TypeScript","PHP","Python","Dart","Rust"]},{"name":"Frontend","keywords":["React","Next.js","Tailwind CSS"]},{"name":"Backend","keywords":["Node.js","NestJS","GraphQL","Prisma","FastAPI","Hono","MercadoPago"]},{"name":"Mobile","keywords":["Flutter","React Native","Ionic","RevenueCat","Codemagic","fastlane"]},{"name":"BaaS & Databases","keywords":["Supabase","Firebase","PostgreSQL","MySQL"]},{"name":"Low-Code & Automation","keywords":["FlutterFlow","GitHub Actions","Make","n8n"]},{"name":"DevOps","keywords":["Docker","Git","GCP","AWS","Vercel"]},{"name":"Testing","keywords":["Playwright","Maestro","Selenium"]},{"name":"GenAI & ML (certified)","keywords":["LLMs","Transformers","Fine-Tuning","PyTorch","Hugging Face","Agentic AI"]}],"languages":[{"language":"Spanish","fluency":"Native"},{"language":"English","fluency":"Full professional"}],"projects":[{"name":"Akashi","description":"Provider-neutral agent framework for Dart & Flutter — a 14-package monorepo published on pub.dev, bringing the agent runtime primitives Python and TypeScript take for granted to the Dart ecosystem. Multi-agent orchestration via subagent-as-tool, control handoffs, and per-step model escalation.","highlights":["Agent runtime: streaming-first tool loop with typed tools and dependency injection, composable stop conditions, and a prepareStep context hook — last-N windowing plus summarize-older-than compaction via a cheaper model.","Multi-provider resilience: FallbackModel fails over across Gemini, OpenAI, and Anthropic behind one contract, taking a shouldFailover(error) predicate to fail over by error type, and blocking mid-stream failover because re-running an emitted stream duplicates output.","Durable execution: versioned Message/Part serialization over a SQLite checkpoint store; human-in-the-loop approvals suspend a run and resume it in another process.","Non-determinism hardening: structured output with self-repair; three providers' streaming formats (text, thinking, tool_use) normalized into one sealed union with exhaustive matching.","Operability: OpenTelemetry tracing, per-call token usage accounting, MCP tools, and bounded-concurrency workflows with retries, backoff, timeouts, and cancellation."],"keywords":["Dart","Flutter","Multi-Agent","MCP","RAG","OpenTelemetry"],"url":"https://akashi.azanello.com"},{"name":"mcp-deep-dive","description":"Protocol-first MCP reference in TypeScript: custom server + client + all 3 capabilities (tools, resources, prompts), both transports (stdio + HTTP), with wire-level JSON-RPC logging. No LangChain wrappers.","highlights":[],"keywords":["TypeScript","MCP","Anthropic","pnpm"],"url":"https://github.com/AleSZanello/mcp-deep-dive"},{"name":"langgraph-langserve-starter","description":"Production-grade REST API template exposing a LangGraph agent via LangServe. Multi-node research agent with SqliteSaver thread-resume, streaming, Langfuse observability, zero-key fake-LLM mode.","highlights":[],"keywords":["LangGraph","LangServe","FastAPI","Python"],"url":"https://github.com/AleSZanello/langgraph-langserve-starter"},{"name":"local-rag-chatbot","description":"Fully-local RAG chatbot built with LangGraph + Chroma + Ollama. Multi-Query Fusion and RRF retrieval, SqliteSaver chat history, pluggable LLM provider. Zero API keys required.","highlights":[],"keywords":["LangGraph","RAG","Chroma","Ollama"],"url":"https://github.com/AleSZanello/local-rag-chatbot"},{"name":"langgraph-ts-agents","description":"TypeScript port of LangGraph supervisor/worker patterns - streaming-first, fully typed with Annotation.Root + Zod, HITL approval, side-by-side Python references.","highlights":[],"keywords":["LangGraph","TypeScript","Multi-Agent","Zod"],"url":"https://github.com/AleSZanello/langgraph-ts-agents"},{"name":"Somnio AI Tools","description":"Open-source CLI that installs and runs AI agent skills, health checks, and security audits for Flutter and NestJS projects across Claude Code, Cursor, Gemini, and other AI coding CLIs.","highlights":["Added the `somnio run` command with interactive model selection, pre-flight validation, and per-step token usage tracking.","Refactored the CLI to a data-driven multi-agent registry (17 agents) and to an Agent Skills plugin architecture with Claude Code plugin support.","Built a custom workflow system for multi-step, multi-model AI task orchestration, plus Cursor CLI support and a setup command for AI CLI installation."],"keywords":["CLI","AI Workflows","Python","Dart","Shell"],"url":"https://github.com/somnio-software/somnio-ai-tools"},{"name":"NovaMX CRM","description":"Real estate CRM with an LLM-powered lead/property classification engine. Public listings + internal lead tracker; agentic scoring runs on Edge Functions on top of Supabase.","highlights":[],"keywords":["Next.js","Supabase","Edge Functions","OpenAI","AI"],"url":"https://novamx.co"},{"name":"Stores Helper","description":"MCP-style CLI exposing Play Store & App Store management (products, forms, subscriptions) as tools for AI agents. Lets coding agents read/write store data from the repo.","highlights":[],"keywords":["CLI","MCP","AI Agents","Play Store","App Store"],"url":"https://github.com/AleSZanello/stores-helper"},{"name":"Spec Dev Ralph","description":"Starter template and guide for Spec Driven Development. Quick entry point for learning and applying the methodology.","highlights":[],"keywords":["Spec Driven Dev"],"url":"https://github.com/AleSZanello/spec-dev-ralph"}],"meta":{"canonical":"https://azanello.com/resume.json","version":"v1.0.0","lastModified":"2026-10-17","pdf":"https://azanello.com/Alejandro_Zanello_Resume.pdf"}}