Versatile Swiss-Portuguese Junior Computer Scientist and AI/ML Engineer. Proven ability to design and deploy scalable architectures, utilizing LiteLLM and Docker to manage high-volume data retrieval and complex systems. …
Versatile Swiss-Portuguese Junior Computer Scientist and AI/ML Engineer. Proven ability to design and deploy scalable architectures, utilizing LiteLLM and Docker to manage high-volume data retrieval and complex systems. Proficient in LangChain/Agentic systems for automating workflows. Quick to adopt new technologies and focused on bridging advanced research with production-ready solutions. Currently completing an MSc thesis in Artificial Intelligence at USI.
<p>• Designed and implemented an agentic system for financial analysis and reporting, capable of boosting analyst efficiency by up to 70% during testing phases.</p><p>• Established core IT infrastructure by deploying containerized services (WebMail, MongoDB, hosting) on a secured VPS domain, ensuring self-managed security for sensitive financial data.</p><p>• Developed targeted agentic workflows for web crawling and data analysis to generate comprehensive market research reports, informing robust financial plan creation.</p><p>• Successfully applied analysis tools in a pilot project (gaming studio client) to drive actionable financial awareness and better client decision-making.</p>
<p>Designed and implemented an automated workflow for financial statement analysis and reporting using agentic systems.<br>
Set up a VPS domain, deploying containerized services (WebMail, MongoDB, and website hosting).<br>
Automated targeted web crawling and data analysis processes with agentic systems, streamlining data ingestion and reporting.</p>
<p>• Engineered a complex, distributed data pipeline infrastructure in two months to retrieve 5GB of longitudinal faculty data from over 100 universities, a scope impractical for manual collection.</p><p>• Achieved high-performance data collection by utilizing LiteLLM to route traffic across 13 different LLM providers, circumventing API rate limits and completing retrieval in just 48 hours of compute time.</p><p>• Designed and implemented an advanced AI agent system (LangGraph/LangChain), reducing data parsing errors from 18% to under 5% across large-scale, heterogeneous web sources.</p><p>• Leveraged Wayback Machine API and Selenium for historical data retrieval, utilizing Supabase and PostgreSQL to manage storage and deliver the final processed data set.</p>
<p>Designed intelligent data pipelines for economic research, using LangGraph/LangChain, multi-provider LLM routing, and Supabase for structured storage.<br>
Led prompt engineering and system oversight with LangSmith.</p>
<p>• Led the complete technical lifecycle (research, customization, and deployment) of the Siza Atlas platform as the sole IT resource, managing the architectural heritage of Álvaro Siza.</p><p>• Successfully deployed the complex Arches Project framework, integrating services such as Elasticsearch on a private Ubuntu server while overcoming significant technical barriers.</p><p>• Engineered a highly maintainable platform environment using Docker containerization.</p><p>• Translated researcher data specifications to structure the digital archive for effective collaborative cataloging and long-term management.</p>
<p>Coordinated staffing and shift scheduling.<br>
Supervised cooking staff and oversaw daily meal preparation as head chef.<br>
Managed stocks.</p>
<p>• Directed all daily operational functions for a high-volume, 200-seat, two-kitchen restaurant over an eight-year tenure, overseeing financial planning, stock management, and quality control.</p><p>• Led culinary operations as Head Chef, supervising a team of three assistants and optimizing kitchen/service workflows for smoother execution during rush hours.</p><p>• Cultivated a high-performance team culture by achieving strong staff retention over several years through organizational clarity and fair scheduling.</p>
<p>• Mentored and guided 23 undergraduate students through core database concepts, relational schema design and advanced SQL querying.</p><p>• Specialized in teaching data modeling using UML Class Diagrams, successfully guiding students through the translation of over 8 conceptual-to-relational models.</p><p>• Customized course material delivery utilizing analogies and repetition, leading to 85% of students reporting high confidence in complex database principles.</p><p>• Instructed practical application across three major full-stack assignments, covering advanced SQL querying, PHP integration, and MySQL database management.</p>
<p>Taught core database concepts and skills, including relational schema design, UML class diagrams, conceptual-to-relational model mappings, SQL, PHP, and MySQL.</p>
<p>Provided personalized and group math tutoring to high school students, aligned with national testing standards.<br>
Designed targeted lesson plans, practice exercises, and review sessions to strengthen students’ problem-solving skills and test-taking confidence, resulting in notable improvements in their exam performance.</p>
<p>Led the research, customization, and deployment of the Siza Atlas collaborative platform for cataloging and managing the cultural heritage of Álvaro Siza’s work using the Arches Project framework.<br>
Implemented and containerized the solution on ISTAR’s private Ubuntu server, ensuring a secure and scalable environment.</p>
<p><u>Information Processing course</u></p><p>⦁ Developed a Flutter application that modelled team productivity using stochastic simulations.</p><p>⦁ Based the model on a strong mathematical foundation, incorporating 11 key lifestyle and resource factors to generate predictive insights.</p><p>⦁ Provided analysis for performance optimization and resource planning in organizational settings.</p>
<p><u>Pilot Project with Hurricane Studios</u></p><p>⦁ Built a custom web-scraping pipeline that collected high-volume market data from 50+ sources, successfully ingesting over 50,000 user feedback entries.</p><p>⦁ Integrated NLP and AI models for sentiment analysis, achieving a comprehensive, meaningful conclusion across the entire dataset within 30 minutes.</p><p>⦁ Delivered interactive dashboards enabling the client to make data-driven decisions based on real-time sentiment analysis and trend detection.</p>
<p>⦁ Developed and deployed an agent-based system to ingest financial statements and automatically generate Swiss GAAP FER compliance reports.</p><p>⦁ Reduced the manual effort required for compliance verification and audit streamlining by approximately 60%.</p><p>⦁ Incorporated advanced data parsing and validation techniques to minimize error rates and ensure high audit validation accuracy.</p><p></p>
<p><u>Deep Learning course</u></p><p>⦁ Pre-processed 200,000 dialog pairs from the Cornell Movie Dialog dataset and trained a custom Transformer model using PyTorch.</p><p>⦁ Designed a 10–12 layer Transformer architecture (trained locally) that achieved more coherent, context-aware responses than standard Seq2Seq approaches.</p><p>⦁ Showcased advanced natural language understanding (NLU) capabilities and expertise in modern deep learning model development.</p>
<p><u>Information Modeling & Analysis course</u></p><p>⦁ Leveraged unsupervised learning techniques (trained on the full TensorFlow library) to automatically identify and decompose large, monolithic Java classes.</p><p>⦁ Improved maintainability and OOP compliance by increasing code cohesion and reducing coupling by 35% across the refactored code base.</p><p>⦁ Automated the refactoring process, enabling a transition toward more modular, maintainable architectures.</p><p></p>
<p><u>Computer Vision & Pattern Recognition course</u></p><p>⦁ Created a video pre-processing pipeline combining classical Computer Vision (CV) techniques (Canny, Hough, DLT) to reconstruct camera perspectives in snooker footage.</p><p>⦁ Achieved an estimated 98% accuracy in projecting the table and ball movements onto a top-down view, significantly enhancing shot analysis and angle measurement capabilities.</p><p>⦁ Informed more accurate performance feedback by enabling clear visual analysis, despite initial video distortions.</p><p></p>
<p><u>High Performance Computing course</u></p><p>⦁ Implemented domain decomposition and parallel computing techniques (MPI) to solve non-linear partial differential equations in C++.</p><p>⦁ Demonstrated high efficiency and distributed computing expertise by achieving near-linear speedup up to 12 cores.</p><p>⦁ Built a scalable system foundational for large-scale scientific simulations.</p><p></p>
<p><u>Distributed Systems course</u></p><p>⦁ Designed a distributed solution for real-time data ingestion of MQTT stream data from a simulated mice lab.</p><p>⦁ Managed real-time ingestion of over 1,000 MQTT data streams per minute into MongoDB and MariaDB.</p><p>⦁ Enabled continuous data capture, monitoring, and scalable analysis, managed via a Flutter frontend, for experimental research.</p><p></p>
The AI-first Recruitment Operating System that unifies and automates the entire hiring lifecycle for modern enterprises worldwide.
Dr Job FZ LLC. 2026 © All Rights Reserved
