Marcello d. looks like a good fit?

We can organize an interview with Aldin or any of our 25,000 available candidates within 48 hours. How would you like to proceed?

Schedule Interview Now

Marcello d. AI, Python and AI Platforms

My name is Marcello d. and I have over 4 years of experience in the tech industry. I specialize in the following technologies: Web Scraping, API, AI Agent Development, Generative AI Prompt Engineering, Machine Learning, etc.. I hold a degree in Bachelor of Technology (BTech), Bachelor of Technology (BTech), Bachelor of Technology (BTech). Some of the notable projects I’ve worked on include: AI Phone Agent Deployment using Lindy.AI, RAG-Based Knowledge Assistant with Re-Ranking (Fully Modular MVP), NaiveRAG – Modular Local Retrieval-Augmented Generation (MVP/POC), MCP Voice Automation Pipeline – Fully Integrable, Agentic Multi-Agent Research & Analysis System (Production-Ready MVP), etc.. I am based in Rio de Janeiro, Brazil. I've successfully completed 21 projects while developing at Softaims.

I approach every technical challenge with a mindset geared toward engineering excellence and robust solution architecture. I thrive on translating complex business requirements into elegant, efficient, and maintainable outputs. My expertise lies in diagnosing and optimizing system performance, ensuring that the deliverables are fast, reliable, and future-proof.

The core of my work involves adopting best practices and a disciplined methodology, focusing on meticulous planning and thorough verification. I believe that sustainable solution development requires discipline and a deep commitment to quality from inception to deployment. At Softaims, I leverage these skills daily to build resilient systems that stand the test of time.

I am dedicated to making a tangible difference in client success. I prioritize clear communication and transparency throughout the development lifecycle to ensure every deliverable exceeds expectations.

Main technologies

  • AI, Python and AI Platforms

    4 years

  • Lovable AI

    3 Years

  • AI Development

    3 Years

  • Langchain

    3 Years

Additional skills

Direct hire

Potentially possible

Previous Company

Movile

Ready to get matched with vetted developers fast?

Let's get started today!

Hire Remote Developer

Experience Highlights

AI Phone Agent Deployment using Lindy.AI

The client hired me to configure a custom AI Phone Agent using Lindy.AI. The core of the project involved not only setting up the agent’s voice and business logic but also applying advanced prompt engineering techniques to ensure natural, accurate, and business-aligned conversations. My work included fine-tuning the tone, intent detection logic, fallback behavior, and knowledge integration to deliver a production-ready voice assistant.

RAG-Based Knowledge Assistant with Re-Ranking (Fully Modular MVP)

RerankRAG is a custom-built AI system that turns raw documents into accurate, context-aware answers. It follows a Retrieve-and-Rerank architecture to extract, reclassify, and generate responses based strictly on the original material. The system is fully modular, API-driven, and designed for real use cases like legal, academic, and enterprise document analysis.

NaiveRAG – Modular Local Retrieval-Augmented Generation (MVP/POC)

Developed a fully operational MVP/POC of a document-aware AI system capable of answering natural language queries by retrieving and interpreting relevant information from uploaded PDF files. The pipeline was structured into independent, modular components (e.g., text extraction, chunking, embedding, retrieval, and response generation), designed for flexibility, clarity, and easy extension. Each module communicates via structured files, enabling pipelined processing and simplified debugging. Ideal for use cases involving legal, research, enterprise documentation, and technical manuals.

MCP Voice Automation Pipeline – Fully Integrable

This Modular Conversational Pipeline (MCP) converts spoken input into clear, natural replies through a fully automated voice loop. Speech is transcribed, intent is interpreted, external content is optionally retrieved, and a contextual response is generated and spoken back. Built to integrate into phone systems, kiosks, or support bots, the agent is modular, headless-ready, and production-grade. No UI or human operator required — just voice in, voice out.

Agentic Multi-Agent Research & Analysis System (Production-Ready MVP)

Developed a fully operational agentic pipeline using modular agents that research, summarize, critique, and write long-form content from live web sources. Built with a modularized-style architecture, this MVP is ready for deployment or customization. It ensures real-time accuracy, prevents hallucinations, and delivers footnoted Markdown reports. Built to serve diverse industries with adaptable intelligence.

Education

  • ETEC

    Bachelor of Technology (BTech) in Electronic engineering

    1987-01-01-1991-01-01

  • University Center -ETEP (Brazil)

    Bachelor of Technology (BTech) in Systems Analyst

  • Universidade Gama Filho

    Bachelor of Technology (BTech) in Computer science

    1994-01-01-1999-01-01

Languages

  • English
  • Spanish
  • Portuguese

Personal Accounts