Ruben S. 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 NowRuben S. Backend, AI and Machine Learning Platforms
My name is Ruben S. and I have over 3 years of experience in the tech industry. I specialize in the following technologies: Python, SQL, Machine Learning, ChatGPT, MongoDB, etc.. I hold a degree in Bachelor's degree. Some of the notable projects I’ve worked on include: Automated Poker Card Detection & Classification System, COMPUTER VISION PROJECT: Densenet architecture, Data Analysis, Artificial Vision- Yolo model, Audio-Text-Video Sentiment Analysis, etc.. I am based in Malaga, Spain. I've successfully completed 7 projects while developing at Softaims.
My passion is building solutions that are not only technically sound but also deliver an exceptional user experience (UX). I constantly advocate for user-centered design principles, ensuring that the final product is intuitive, accessible, and solves real user problems effectively. I bridge the gap between technical possibilities and the overall product vision.
Working within the Softaims team, I contribute by bringing a perspective that integrates business goals with technical constraints, resulting in solutions that are both practical and innovative. I have a strong track record of rapidly prototyping and iterating based on feedback to drive optimal solution fit.
I’m committed to contributing to a positive and collaborative team environment, sharing knowledge, and helping colleagues grow their skills, all while pushing the boundaries of what's possible in solution development.
Main technologies
Backend, AI and Machine Learning Platforms
3 years
Python
1 Year
SQL
1 Year
Machine Learning
2 Years
Additional skills
- Python
- SQL
- Machine Learning
- ChatGPT
- MongoDB
- PyTorch
- YOLO
- Git
- TensorFlow
- Keras
- Deep Learning
Direct hire
Potentially possible
Previous Company
IBM Spain
Experience Highlights
Automated Poker Card Detection & Classification System
Developed a robust two‑stage computer‑vision pipeline to automatically detect and classify playing cards in images. In Stage 1, I fine‑tuned a Faster R‑CNN model on COCO‑formatted data to localize each card. In Stage 2, I built specialized ResNet18 classifiers (with mixup & TTA) for suits and numbers and integrated an optional YOLOv12 model for unified full‑card classification. Finally, I orchestrated detection, cropping, model ensembling and NMS in a Python API (card_detector.py), delivering end‑to‑end inference, visualization tools, and performance reports.
COMPUTER VISION PROJECT: Densenet architecture
I developed a custom DenseNet-169 architecture from scratch in PyTorch to showcase my expertise in advanced CNN design. This project demonstrates how each component—initial block, dense blocks, transition blocks, and classification layers—integrates to form an efficient, high-performing model for image classification. I also validated the implementation using synthetic data, confirming correct forward/backward passes and parameter updates.
Data Analysis
This project aims to provide a comprehensive view of the luxury property market in Madrid. We cover data cleaning, exploratory analysis, property segmentation and key insights for potential investors and real estate professionals.
Artificial Vision- Yolo model
The project involves setting up and training a YOLO model for football object detection using a custom dataset The environment is set up in Google Colab, and necessary packages like ultralytics and OpenCV are installed. A dataset for football player detection is downloaded from Roboflow and prepared for training. The YOLO model is trained to detect objects like football, goal mouth, referee, and players from two teams. The training process involves specifying custom data in a YAML file, defining the training and validation datasets, and training the model using specified epochs and image size.
Audio-Text-Video Sentiment Analysis
Project Description: Multimodal Emotion Analysis System This project aims to develop a comprehensive emotion analysis system capable of processing and interpreting text, audio, and video to identify human emotions. The system integrates machine learning models and leverages deep learning techniques for emotion detection and classification. The project is structured to handle different data modalities, including natural language text, speech, and facial expressions, providing a holistic approach to emotion analysis.
Education
Universidad de Málaga
Bachelor's degree in
2020-01-01-2024-01-01
Languages
- English
- Spanish
Github