Email: fabio.cancio.sena@gmail.com | Phone: +55 61 992015000 LinkedIn: https://linkedin.com/in/fabio-sena-mlengineer

Hey there! I'm Fábio Sena, a Senior Machine Learning Engineer at NuBank, passionate about tackling intriguing machine learning problems. With seven years of experience, I've explored the lesstraveled paths, collaborating with tech industry leaders to deliver innovative and game-changing solutions.

My expertise lies in weaving together machine learning, cloud computing, algorithms, and data structures to build highly efficient and scalable models. At Appen, I successfully deployed nearly 30 models in production, while also contributing to the design and migration of ML cloud architecture, enhancing scalability and efficiency. Additionally, I possess expertise in computer vision and natural language processing.

During my time at behup, I designed a robust cloud data architecture utilizing Spark and Elasticsearch. This enabled efficient management, processing, and searchability of millions of data points, providing valuable data-driven insights. Leveraging classical machine learning and NLP techniques, I extracted valuable information from textual data, facilitating decision-making.

My background in software architecture enables me to envision the bigger picture and build robust, scalable systems. By fitting ML solutions seamlessly into broader tech frameworks, I ensure smooth and efficient outcomes.

Apart from my practical experience, I hold an MBA in Data Science and Big Data, enhancing my planning, cloud computing, communication, and advanced data analytics skills. My capstone project on CV Object Detection showcased cutting-edge computer vision techniques.

As an advocate of lifelong learning, I stay updated with the latest advancements in the field. Fluent in English, Portuguese, and Spanish, I thrive in collaborating with multicultural teams to deliver impressive results.

Creating scalable and reliable machine learning models that make a real difference fuels my passion. If you have a project or an idea you'd like to discuss, I'm eager to listen. Let's connect and leave our mark in the world of machine learning together!

• Programming Languages: Python, SQL
• Cloud Computing and Big Data: Amazon Web Services (AWS), AWS SageMaker, Cloud Computing, Data Engineering, Apache Spark, Hadoop, Distributed Computing
• **Machine Learning Libraries and Techniques: PyTorch, TensorFlow, Scikit-Learn, Natural Language Processing, Reinforcement Learning, Unsupervised Learning, Convolutional Neural Networks (CNN), Generative Adversarial Networks (GANs), Predictive Modeling
• Deep Learning and Natural Language Processing Models: BERT, GPT-3
• MLOps and CI/CD: Docker, Kubeflow, Machine Learning Pipeline, Continuous Integration and Continuous Delivery (CI/CD), Airflow, Kubernetes, MLOps
• Advanced and Emerging Fields: Differential Privacy, Federated Learning, LlamaIndex, LangChain
• Soft Skills: Effective Communication, Problem Solving, Critical Thinking, Project Management, Teamwork/Collaboration, Adaptability, Emotional Intelligence

• Led development of ML solutions for Appen, a data labeling company, including image deduplication, batch inference, and trainable models using transfer learning
• Designed and built stream-based real-time ML architecture using Apache Kafka
• Developed cutting-edge computer vision models for face detection and blurring, license plate detection and blurring, text transcription, car object detection from LiDAR data, and label bounding boxes in street scene images
• Designed and implemented models for audio/speech processing and speaker diarization
• Built a dashboard to report ML model usage by projects, clients, and periodicity using Mode Analytics

• Created a suite of 6 products to understand consumer buying behavior and product pricing strategy using alternative choice modeling techniques and large data samples
• Evaluated video ad's effectiveness using data science and neurosciences
• Built a product to automatically understand consumer opinions from videos and audio using speech-to-text and a combination of NLP techniques

• Designed and implemented an end-to-end ML pipeline for Luiza.ai, including credit default risk prediction and customer recommender system using cluster analysis

• Implemented a scalable and trainable message-based ML architecture using AWS SageMaker, Kafka, AWS EventBridge, SNS, SQS, and Batch Transformer
• Developed a natural language processing pipeline to extract valuable information from legal case files in PDF format, grouping related files into hierarchical clusters
• Built a customer-centric recommender system using cluster analysis and the R library RecommenderLab
• Built an end-to-end pipeline using XGBoost to predict credit default risk
• Used advanced business analytics to create predictive models

• MBA in Data Science and Big Data - IGTI - Institute of Management in Information Technology - 2016 - 2017
  • Focused on management, big data, statistics, data science, and machine learning.
  • Relevant coursework includes infrastructure and cloud computing, big data fundamentals, data modeling with Hadoop, statistical analysis, and machine learning applied to big data.
• Bachelor's degree, Bachelor's Degree in Information Systems - UniEuro - Euroamerican University - 2000 - 2004