open to interesting problems

Franco Rupnik

Software Engineer — backend, distributed systems & AI platforms

I build scalable services and AI-driven systems for production — from Spring Boot microservices on Kubernetes to agent-tool interfaces over the Model Context Protocol.

whoami

Backend at the core, AI at the edge.

I'm a software engineer focused on backend development, distributed systems and cloud-native architectures. I work across Java, Python, Go, Docker, Kubernetes and AWS, building scalable services and AI-driven applications that run in production.

At Mendel, I build the AI platform behind intelligent expense management — a Spring Boot microservices ecosystem on AWS EKS. I own the WhatsApp conversational experience end to end: a Java orchestration layer and a Python AI agent for natural-language understanding and tool-based workflows.

I built and shipped our MCP (Model Context Protocol) server to production, exposing expense-audit and travel-approval tools to AI assistants like Claude — with an OAuth 2.0 authorization layer (Dynamic Client Registration, refresh tokens), delegated SSO and SSE streaming transport. Previously at Accenture I architected multi-agent AI systems with RAG pipelines, and I teach Microservices Architecture at ITBA.

focus[]

What I care about building

01

AI / LLM orchestration

Intelligent automation and agent workflows that hold up under real production traffic.

02

MCP & agent-tool interfaces

Model Context Protocol servers that expose real tools to AI assistants, safely and with auth.

03

High-performance backend

Services tuned for latency, throughput and cost — where the numbers actually matter.

04

Cloud-native systems

Containerized workloads on Kubernetes, with the CI/CD and observability to keep them healthy.

05

Distributed architectures

Microservices that stay resilient as they scale, communicating over well-defined contracts.

git log --experience

Where I've been building

● now · Jan 2026 →

Backend Engineer — AI Platform

Mendel

Building the AI platform for intelligent expense management on Spring Boot microservices + AWS EKS. Owner of the WhatsApp conversational experience (Java BFF + Python AI agent) and of our production MCP server with OAuth 2.0, delegated SSO and SSE streaming.

in parallel · 2025 →

Adjunct Professor — Microservices Architecture

ITBA

Teaching and mentoring students in the design and implementation of microservice-based systems — lectures, hands-on labs and real-world exercises with Docker, Kubernetes, cloud-native tooling and modern communication patterns. Focused on deploying, scaling and observing distributed systems.

Aug 2024 → Jan 2026

AI & LLM Technology Architecture

Accenture

Built a multi-agent AI system on a customized n8n fork that routes user queries to specialized agents — designing agent workflows, integrating RAG pipelines and optimizing LLM response quality. Earlier, as an intern, worked across RAG/GraphRAG, prompt engineering and fine-tuning to improve enterprise-chatbot accuracy, cost and performance.

education --list

Where I studied

2020 → 2025

Computer Engineering — B.Eng. & M.Eng. level

Instituto Tecnológico de Buenos Aires (ITBA)

Six-year Computer Engineering degree (Bologna framework — B.Eng. + M.Eng. level), with a graduate focus on Software Architecture & Engineering.

work[]

Selected & open-source projects

Docker Monitor

Monitoring and operational automation for Docker environments — my ITBA final project.

GoPythonShell

TaskComposer

A microservices system to orchestrate and manage distributed tasks reliably at scale.

GoJavaDocker

ReviewRealm

Full-stack review app with a RESTful HATEOAS API — Spring + Hibernate backend, Angular front.

JavaSpringAngular

Bandoru

A cloud service for secure code sharing, deployed on AWS with Infrastructure as Code.

TypeScriptPythonAWS

Bizcocho OS

A low-level OS project: process scheduling, memory management and multitasking, close to the metal.

CAssembly

Stronk & Stronk App

A fitness platform across web (Vue) and a native Android app (Kotlin) for tracking workouts.

VueKotlin

See everything on GitHub →

stack --list

Tools I reach for

languages
JavaPythonGoTypeScriptC
infra & cloud
DockerKubernetesAWS EKSCI/CD
backend
Spring BootMicroservicesOAuth 2.0SSE
ai / llm
MCPLLM orchestrationAgent workflowsRAG

contact

Let's build something

university
frupnik@itba.edu.ar
links

LinkedIn · GitHub