// AI Engineer & Software Engineer

Agustín
Pérez

Building production-grade AI systems that deliver measurable impact. Specialized in semantic search, agent orchestration, and large-scale embedding pipelines.

0%
Conversion Uplift
0K+
Products Indexed
0%
Latency Reduction
Agustín Pérez
Available for opportunities
scroll

Professional Profile

AI Engineer with strong Software Engineering foundations and hands-on experience designing and deploying scalable, production-grade AI systems in the e-commerce domain.

Specialized in semantic search, agent orchestration, and large-scale embedding pipelines using modern LLM frameworks and vector databases.

I focus on building reliable, high-performance AI systems that enhance user experience, ensure operational robustness, and drive real business outcomes.

Location Tandil, Buenos Aires, Argentina
Languages English (B2) · Spanish (Native)
Education Software Engineering · UNICEN

Professional Experience

Mar 2026 — Present Current

Ssr Python Engineer

MAX CONTINENTAL
  • Developing robust, strongly-typed APIs to power an AI-driven search and matching system for medical product catalogs using the OpenAI API.
Python OpenAI API FastAPI
May 2025 — Feb 2026

AI Engineer

Region Global eCommerce Agency
  • Designed and deployed a Semantic Search Engine using OpenAI Embeddings and Elasticsearch for 600K+ product catalogs — reducing no-result queries by 35% and improving search-driven conversion by 18% within Q1.
  • Implemented caching and indexing optimizations that cut p95 search latency by 40%.
  • Built a parallel embedding generation pipeline with Redis, significantly reducing API costs and enabling efficient high-volume processing.
  • Developed an automated product description generator using prompt engineering, reducing manual content creation by 70%.
Python OpenAI Embeddings Elasticsearch Redis RAG Prompt Engineering
Nov 2024 — Apr 2025

Backend Developer

Tandil Public Health System (SISP)
  • Reduced manual effort by ~90% by automating end-to-end medical record submissions citywide via a RESTful API.
  • Implemented JWT authentication and comprehensive Postman testing for secure, compliant handling of sensitive data.
Java Spring Boot PostgreSQL JWT
Nov 2023 — Aug 2024

SQL Freelance Developer

Fiverr
  • Delivered 15+ custom database solutions, earning consistent 5-star ratings through high-quality code and proactive client communication.
SQL PostgreSQL MySQL

Technical Stack

AI & Machine Learning

OpenAI API LLMs RAG MCP Prompt Engineering TensorFlow Keras Reinforcement Learning Scikit-learn NumPy Pandas

Frameworks & Orchestration

LangChain LangGraph FastAPI Spring Boot RASA Redis n8n

Languages

Python Java JavaScript PHP

Databases & Cloud

Elasticsearch ChromaDB PostgreSQL MySQL Docker AWS CI/CD

Featured Projects

Nov 2025 Agent Systems

Ambient Email Agent

Stateful email agent from LangChain Academy with persistent memory and human-in-the-loop mechanisms. Full deployment on LangGraph Platform with LLM-as-a-judge evaluation and traceability via LangSmith.

LangChain LangGraph LangSmith Python
Apr 2025 Hackathon · Microsoft

VeriBot

Conversational AI agent for real-time news fact-checking. Implements a RAG workflow with GPT-4 + SerpAPI for multi-source verification, delivering unbiased summaries with a truthfulness indicator. Deployed on Azure Container Apps.

Java LangChain4J Azure ChromaDB Spring Boot
View on GitHub →

Education & Certifications

Degree

Software Engineering

National University of Central Buenos Aires (UNICEN)

5-year degree completed in 4.5 years · Average grade: 8.05 / 10

Certification · DataCamp

AWS Cloud Practitioner (CLF-C02)

Amazon Web Services
Certification · DataCamp

Associate AI Engineer for Developers

DataCamp

OpenAI API · LangChain · Vector Databases · Embeddings · LLMOps

Certification · freeCodeCamp

Machine Learning with Python

freeCodeCamp · 300 hours

Deep Neural Networks · CNNs · Reinforcement Learning · Optimization

Highlights & Writing

Technical Article

Multi-Query Retrieving in RAG Systems

Why single queries fail in complex RAG systems — and how generating multiple reformulated queries from different perspectives dramatically improves retrieval quality and LLM response accuracy.

Read on LinkedIn →
Event · UBA

1st Deep Learning Spring School at UBA

Intensive program at Universidad de Buenos Aires covering Diffusion Models, LLM training & scalability, advanced evaluation metrics, agent-based security automation, and optimization methods.

View post →
Hackathon · Microsoft

Microsoft AI Agents Hackathon 2025

Built VeriBot with teammates — a RAG-powered conversational agent for real-time news fact-checking using Azure Bot Service, GPT-4, and cross-source truthfulness analysis. Open source on GitHub.

View project →

Get in Touch

Open to new opportunities, collaborations, and interesting problems in AI engineering. Let's build something impactful together.