Junior Full Stack and AI Developer
VITOR
SILVA
I build web applications end to end — Python and FastAPI on the back end, React and Next.js on the front — and add AI where it earns its place.
After 14 years running critical operations at Correios, I build software the way I ran operations: measured, documented and designed not to fail.
Engineering Product,
Not Just Code.
With 14 years of mission-critical operations experience, I don't just write scripts—I architect resilient systems. I've spent over a decade managing high-pressure logistics where downtime means total failure. That operational maturity is the foundation of my engineering.
I focus on systems that are observable, gracefully degrading, and maintainable. I build solutions to solve the real business problem, not just the technical challenge.
I operated for 14 years in zero-tolerance-for-failure environments. That mindset translates to defensive coding, robust error handling, and architectures built for resilience.
I understand business processes because I managed them for over a decade. I design solutions that deliver real-world outcomes.
What I bring
to your team.
Remote-first, based in Curitiba. Open to junior full stack and AI developer roles.
React and Next.js front ends over Python or Node APIs, with authentication, a database and a deploy pipeline.
High-performance async backends integrating AI models, databases and external services.
Architecture and development of stateful agents with memory, multi-agent orchestration and robust decision flows.
High-fidelity semantic retrieval pipelines for Q&A, support and enterprise knowledge bases.
Multi-LLM audit systems that mitigate hallucinations before they reach the user. Cost control and groundedness.
I turn operational processes into software: map the flow, find where it fails and automate the repetitive part.
Based in Curitiba, Brazil. Available for remote roles in Brazil and abroad. Technical English.
Yes. I am looking for a junior full stack or AI developer position, remote or hybrid in Curitiba. I bring 14 years of operations experience and a portfolio of projects I built and shipped.
Build and ship features end to end on a Python and React stack, write tests and document what I build. TypeScript and cloud are where I am still growing.
Yes. I read technical English fluently and I am comfortable with remote, asynchronous work.
A regular chatbot answers from what the model was trained on — it can hallucinate or be outdated. RAG retrieves real information from your data before answering, ensuring accuracy and traceability.
Tools.
Not just buzzwords.
Architectures that
generate business value.
The real challenge isn't building AI — it's trusting it in production. My projects target governance, guardrails and hallucination control.
MestreGrana
High risk of hallucination and lack of governance in generative AI for financial advice.
Architecture:- Stateful orchestration via LangGraph for long-term memory.
- "Judge" LLM system to audit answers (Guardrails).
FluencyForge
Teaching personalization at scale hits LLM context limits.
Architecture:- Dynamic RAG coupled with stateful memory to maintain historical context.
TwinRank AI
Popularity-based recommendation systems fail in personalization.
Tech Stack:PyTorch, FastAPI, DVC, MLflow
Aether Oncology
Robust clinical data integration for multi-platform interfaces.
Tech Stack:FastAPI, Python, React, Flutter, Node.js
VektorWork
AI tools for careers and freelancing send sensitive data, like CVs and expectations, to third-party clouds.
Tech Stack:FastAPI, LangGraph, Ollama, Flutter, Electron, Playwright, SQLite, Docker
RetentIA
High churn rates in SaaS platforms due to reactive support.
Tech Stack:Python, Scikit-learn, XGBoost, FastAPI
Harmoniz.AI
Scalably correlating complex biometric data.
Tech Stack:Python, Pandas, LLM Pipeline
AIClinicOS
Modern clinics need intelligent OS to manage data and patient care efficiently.
Tech Stack:Next.js, Tailwind, Supabase
Rankium Systems
B2B service operations need one governed platform for leads, contracts and payments, with each organization's data kept apart.
Tech Stack:FastAPI, Next.js 15, PostgreSQL, Redis, Stripe Connect, WebSockets
VITORIUM
A hospital needs incoming medical reports triaged by urgency, with a model that can be retrained, monitored and served fast.
Tech Stack:Python, scikit-learn, FastAPI, ONNX Runtime, Airflow, Docker, Prometheus, Grafana
Corpo em Ação
Generic training apps ignore the user's goal and equipment, and give no clear view of progress.
Tech Stack:Flutter, Dart, Hive, OpenAI API with offline fallback, ExerciseDB
Long-term memory and retrieval layer for an AI agent: vector search plus PostgreSQL state.
Space action game built with Unity and C#, my first game.
GITHUB →Molecular structures modeled as graphs, in Python.
GITHUB →High-conversion landing page for an e-book, built on 58 scientific sources.
Operational maturity.
Cutting-edge stack.
Plenty of juniors can write the code. Few have spent 14 years in mission-critical operations learning what makes a system resilient.
Reliability mindset forged through high-pressure operations and problem-solving in environments that do not tolerate failures.
- SLA guarantee and large-scale operational continuity
- Technical focal point for corporate system implementation
- Analytical profile for real-time failure mitigation
- Formal foundations in algorithms, systems and distributed computing
- Complementary tracks: MLOps, FastAPI and Data Engineering
- MLOps, model deployment and ML pipelines in production
- Scalable AI system architecture and model governance
Building web applications and AI systems end to end: back end, front end and deployment.
- Stateful agentic systems with memory and LangGraph orchestration
- FastAPI services with async patterns and high performance
- RAG pipelines designed for real use cases with semantic precision
Let's build the
next level?
Open to junior full stack and AI developer roles, remote or hybrid in Curitiba. Fourteen years of operational discipline, plus software I built and shipped.