
Rodrigo Heck
Verified Expert in Engineering
Data Science Developer
Lisbon, Portugal
Toptal member since January 28, 2022
Rodrigo is a data scientist with experience in data communication and analysis, interactive data visualization, and web development. He focuses on developing solutions with AI, natural language processing, and computer vision and embedding them in user-friendly applications. Rodrigo enjoys building transformative systems using the best technology and solving problems by delivering quality solutions using algorithms, data, and creativity.
Portfolio
Experience
- Generative Pre-trained Transformers (GPT) - 3 years
- Data Science - 3 years
- Natural Language Processing (NLP) - 3 years
- Machine Learning - 3 years
- R - 3 years
- Python - 3 years
- Keras - 3 years
- React - 2 years
Availability
Preferred Environment
Jupyter Notebook, Visual Studio Code (VS Code)
The most amazing...
...project I've developed is a platform that gathers different Brazilian fashion eCommerce platforms in one website powered by a sophisticated search algorithm.
Work Experience
AI Developer
Michael Sullivan & Associates LLP
- Developed a retrieval augmented large language model (LLM) that could leverage internal data to provide better answers in a chatbot setting.
- Built a chatbot platform from scratch, setting up both front- and back-end architectures.
- Developed an internal method for information retrieval composed of multiple steps.
Data Scientist
SPODIO
- Automated the process of campaign poster creation by finetuning stable diffusion on proprietary data.
- Leveraged GPT family models to automatically generate important insights from text data.
- Created dashboards analyzing social media information about the company.
- Helped to put in place a recommendation algorithm based on user demographics and platform interactions.
Full-stack Developer
Wispr AI
- Developed a real-time dashboard able to display the signal from physical sensors.
- Created a back-end system that allowed low latency data communication in a continuous setting using sockets.
- Implemented a system to record data from physical sensors to build a dataset for machine learning training.
CEO
Typercast
- Developed a platform that enabled users to do simple searches that return posts related to the input on social media.
- Used zero-shot learning to leverage AI for text classification.
- Implemented the back-end structure, including the APIs, databases, and file storage.
- Developed a customizable dashboard that allowed the user to investigate data returned from social media.
Data Scientist
James Tip
- Elaborated visually compelling dashboards that could help the clients better navigate their data.
- Maintained and improved the code used to provide purchase recommendations to the clients.
- Created new methods to identify and avoid stockouts.
Data Scientist
Data Science Brigade
- Conducted thorough statistical analysis on large datasets of clients.
- Elaborated presentations that contained the most critical findings from our investigations.
- Applied machine learning to automatically discover what most impacted the success of the client's business.
Junior Data Scientist
Postmetria
- Used natural language processing and other artificial intelligence methods to assess the NPS of client companies, resulting in a better synthesis of consumer sentiment on social networks.
- Built interactive visualizations in dashboard formats and automatic reports to communicate valuable information internally and externally.
- Developed Bayesian models that could measure the impact of interventions in a real-life scenario or the non-experimental environment.
Experience
Shelves Identification
I developed the AI algorithms necessary to segment and classify each product and the platform that would enable the client to manually label the brands for training purposes. All solutions were encapsulated in a simple-to-use API that received an image and returned the distribution of products and brands.
Automatic Reports
Our company collected a lot of social media comments about our clients. Still, most of the interaction they had with this data was by checking the overall sentiment displayed as a single number.
My intention with this project was to automatically generate a Shiny application that offered all the important information they wished to know in a single place. They had access to previously calculated metrics and could interact with the graphs and comments, conduct customized searches, and generally have a better overall understanding of their data.
The clients to which we introduced this solution were satisfied with the tool. They enjoyed this guided but not static experience to know what happened over a certain period regarding their social media presence.
Consulting Marketplace
Dataset Gathering from Multiple Surveys
Internal Chatbot for Law Firm
Education
Bachelor's Degree in International Relations
Universidade Federal do Rio Grande do Sul - Porto Alegre, Brazil
Specialization in Urban Economics
University of Göttingen - Göttingen, Germany
Certifications
MicroMasters in Statistics and Data Science
MITx on edX
Skills
Libraries/APIs
Pandas, Keras, TensorFlow, Firebase Web SDK, NumPy, TensorFlow Deep Learning Library (TFLearn), Scikit-learn, React, PyTorch, X (formerly Twitter) API, Stripe, Stripe API, Stripe Connect API, Socket.IO
Tools
Net Promoter Score (NPS), Plotly, Amazon SageMaker, BigQuery, GitHub
Languages
R, Python, Python 3, SQL, HTML, CSS, JavaScript, TypeScript
Frameworks
Flask, RStudio Shiny
Platforms
Jupyter Notebook, Firebase, Visual Studio Code (VS Code), Docker, Amazon, Amazon Web Services (AWS), Google Cloud Platform (GCP), Vertex AI
Storage
Firebase Realtime Database, Cloud Firestore, JSON
Paradigms
Text Retrieval
Other
Natural Language Processing (NLP), Dashboards, Hugging Face, Data Analytics, Market Research, Marketing Research & Analysis, Data, Generative Pre-trained Transformers (GPT), Retrieval-augmented Generation (RAG), Probability Theory, Machine Learning, Data Analysis, Data Visualization, Statistics, Data Science, Computer Vision, Web Scraping, Naive Bayes, Deep Learning, Clustering, Topic Modeling, Statistical Methods, Linear Regression, Long Short-term Memory (LSTM), Convolutional Neural Networks (CNNs), Front-end, visNetwork, Artificial Intelligence (AI), Computer Vision Algorithms, Analytics, Generative Pre-trained Transformer 3 (GPT-3), Economics, Politics, Economic Analysis, Bayesian Statistics, APIs, Gunicorn, Data Engineering, Back-end, Full-stack, Containers, Jitsi, Data Structures, Recommendation Systems, Chatbots, OpenAI GPT-4 API, LoRa, Gemini
How to Work with Toptal
Toptal matches you directly with global industry experts from our network in hours—not weeks or months.
Share your needs
Choose your talent
Start your risk-free talent trial
Top talent is in high demand.
Start hiring