$whoami --verbose

role: AI EngineerAvailable

branch: main

Joan Pellegrino

AI Engineer | GenAI & LLM Systems

Building intelligent systems that connect LLMs, enterprise data, APIs, and cloud infrastructure.

Explore Projects

GitHub LinkedIn Emailjoanpellegrino04@gmail.com

5+Years Exp.

Enterprise AISpecialization

99.9%Uptime SLA

Multi-AgentArchitecture

Talk to my AI

Don't scroll. Just ask.

Ask about my projects, stack or experience

Tap and talk to my AI about my work.

Tap to talk

This site doesn't save your audio. Your voice is processed in real time by Google Gemini. Basic session metrics are recorded.

Autonomous agent systems, integration pipelines, and production tools

Featured Projects & Architecture

joanp101/enterprise-agent-orchestrator

Private

Enterprise · Multi-Agent

Enterprise Multi-Agent Intelligence System

Stateful multi-agent system built with Google ADK and LangGraph, orchestrating specialized agents for autonomous enterprise workflows. Includes a RAG-powered Document Intelligence agent for semantic retrieval from technical documentation, a Text-to-SQL agent with schema validation and read-only security controls, and a support orchestration layer that routes queries across knowledge bases, databases, and APIs.

Multi-Agent Orchestration · RAG · Text-to-SQL · Stateful Graph

PythonLangGraphGoogle ADKRAGText-to-SQLDynamoDBAWS EKS

# LangGraph Multi-Agent Orchestrator

graph = StateGraph(EnterpriseState)

graph.add_node("router", IntentRouter)

graph.add_node("etl_agent", TextToSQLAgent)

graph.add_node("support_l1", AutonomousL1Agent)

graph.set_entry_point("router")

agent_runtime = graph.compile()

Case Study

joanp101/smart-parser-claude-plugin

Private

Production Tooling

Smart-Parser Claude Plugin

Custom Claude plugin with specialized agentic skills to generate resilient parsers and validation scripts for complex files, drastically accelerating the creation cycle of data ingestion routines.

LLM-Powered Agentic Skills · Claude API · Python

Claude APIPythonPrompt EngineeringParser Engine

# Claude Custom Skill: File Parser Engine

@claude_skill("parse_complex_stream")

async def generate_parser(stream: ByteStream):

schema = await inspect_schema(stream)

return ASTParser(schema).build_ingestion()

joanp101/distributed-event-pipeline

Private

Cloud Data Architecture

Distributed REST API & AWS S3 Ingestion Engine

High-throughput data ingestion and ETL architecture connecting heterogeneous sources (RESTful APIs, SFTP, AWS S3, GCS) to Snowflake and PostgreSQL with Pandas data transformation and fault-tolerant serverless pipelines.

Millions of daily events · Serverless REST API Integration

PythonPandasRESTful APIsAWS S3AWS LambdaSnowflakePostgreSQL

# REST API & AWS S3 Ingestion Engine

raw_data = fetch_api_payload("https://api.enterprise.com/v1")

df = pd.DataFrame(raw_data).transform()

upload_s3_bucket(df.to_parquet(), bucket="s3://enterprise-lake")

df.to_snowflake("enterprise.raw_analytics")

joanp101/portfolio

main

Live demo

Voice AI Agent for Portfolio

Real-time conversational voice agent embedded in this site. Visitors can talk to an AI that answers questions about my projects, stack and experience, with a state-driven interface (idle, listening, thinking, speaking) and audio processed by Google Gemini.

Gemini Live API · State Machine · Audio Context

GeminiWeb Audio APIWebSocketsAstro

# Real-time Web Audio API & Gemini WS

this.ws = new WebSocket(geminiWsUrl)

this.mic = new MicCapture(ctx, sendAudioChunk)

Architecture Try it live

Technologies & Professional Journey

Stack & Experience

01.AI & GenAI Engineering

11 tools

Google ADKLangGraphLangChainMCP (Model Context Protocol)Multi-Agent OrchestrationRAGText-to-SQLGemini APIAnthropic Claude APIOpenAI APIVector Databases

02.Cloud & Infrastructure

10 tools

AWS EKSAWS LambdaAWS BatchAmazon CloudWatchDynamoDBAmazon S3Amazon SQS (DLQ)API GatewayGCP (BigQuery, GCS)Serverless & Event-Driven

03.Data & Languages

10 tools

PythonPySparkApache KafkaSQLPostgreSQLSnowflakeBigQueryETL/ELT PipelinesRESTful APIsFinancial Formats (MT940, Parquet)

04.Tools & DevOps

7 tools

GitDockerCI/CDAWS GlueSFTPAstroTailwind CSS

Senior AI & Integrations Engineer

Simetrik

commit 2020..Sept 2026

Led the design, architecture, and production deployment of enterprise Artificial Intelligence solutions (Multi-Agent Systems, RAG, Text-to-SQL) and large-scale financial integration infrastructure:

Designed and deployed a stateful multi-agent system on AWS EKS using Google ADK and LangGraph (Router + Specialists pattern) to autonomously resolve operational queries, diagnose CloudWatch logs, and orchestrate re-executions in AWS Batch with persistent memory in DynamoDB.
Built a conversational Text-to-SQL agent connected to PostgreSQL via MCP (Model Context Protocol), implementing strict schema validation, read-only security controls, and contextual explanations for business teams.
Developed a semantic extraction and RAG pipeline over technical documentation and unstructured contracts, enabling non-technical teams to query knowledge bases in natural language and reducing operational reliance on specialists.
Created the Smart-Parser Claude Plugin with Python agentic skills to automatically generate, validate, and audit data parsers and complex ETL scripts, accelerating the delivery and integration cycle in Git.
Architected and implemented enterprise ETL/ELT pipelines across REST APIs, SFTP, AWS S3, GCS, BigQuery, PostgreSQL, and Snowflake, processing millions of daily financial transactions with 99.9% uptime (SLA).
Implemented fault-tolerant, asynchronous synchronization using Apache Kafka, webhooks, AWS Lambda, API Gateway, and Amazon SQS (DLQ), alongside Python and PySpark validation engines to reconcile financial files (MT940, structured PDFs, CSV, and Parquet).

PythonGoogle ADKLangGraphAWS EKSMCPRAGText-to-SQLApache KafkaPySparkSnowflakePostgreSQLDynamoDBAWS Batch

✦ About

I engineer intelligent systems.

AI / GenAI Engineer and Senior Integrations Specialist with nearly 6 years of experience building distributed systems, data pipelines, and production AI applications.

I design and deploy production-grade AI systems, ensuring Large Language Models connect securely, deterministically, and reliably with enterprise data sources and cloud infrastructure:

I architect and deploy stateful Multi-Agent systems (Router + Specialists pattern) using Google ADK and LangGraph on AWS EKS with persistent memory in DynamoDB.
I build secure Text-to-SQL conversational agents connected to relational databases (PostgreSQL) via MCP (Model Context Protocol), enforcing strict schema validation and read-only controls.
I develop semantic extraction pipelines (RAG), custom agentic developer tools with Claude API, and real-time voice agents powered by Gemini Live API over WebSockets.
I bring nearly 6 years of financial data engineering at Simetrik, architecting event-driven ETL/ELT pipelines (Python, PySpark, Snowflake, BigQuery, Kafka, AWS Serverless) processing millions of daily transactions with a 99.9% uptime SLA.

View Resume

// engineering evolution

Enterprise Systems

Integrations & APIs

Cloud + Data Engineering

Distributed Systems

AI / GenAI Systems

Previously at

Simetrik

Location

Colombia

Education

Computer Science — University of Córdoba

commit 2015..2019

Hackathon

FRONTIER AI Builders Hackathon (Oct 2026) - 'The Black Box' challenge, team entry: replaced a legacy system, passing 99 of 100 hidden tests; ranked 8th of 38 teams.

"The most reliable AI systems are built on solid engineering foundations — connected to real data, designed for production, and grounded in the systems they automate."

Joan Pellegrino · AI Engineer | GenAI & LLM Systems

Let's connect

Get in Touch

$init --collaborate

Let's build something intelligent

Open to opportunities in AI Engineering, GenAI, and LLM Systems.

Get in Touch

or find me at

joanpellegrino04@gmail.com