Jose Luis Moreira Arruda, Developer in São José dos Campos - State of São Paulo, Brazil
Jose is available for hire
Hire Jose

Jose Luis Moreira Arruda

Data Scientist and Python Developer

São José dos Campos - State of São Paulo, Brazil

Toptal member since April 19, 2023

Bio

Jose is a senior AI/ML engineer who's experienced across multiple sectors, including eCommerce, healthcare, and fintech. He is an expert in developing strategic projects and building AI/data products. He easily translates pain points and business goals into tailored AI products and designs. He deploys machine learning and deep learning models for time series, CV, and NLP and integrates them into company systems on the cloud. Jose has led data science projects while mentoring colleagues.

Portfolio

Outdoor Living Supply - Main
Python, Generative Artificial Intelligence (GenAI), Full-stack Development...
Flinks
Deep Learning, Generative Pre-trained Transformers (GPT)...
Farfetch
Computer Vision, Deep Learning, PySpark, Machine Learning...

Experience

  • Data Science - 8 years
  • Artificial Intelligence (AI) - 7 years
  • Python - 7 years
  • Machine Learning - 7 years
  • Solution Architecture - 6 years
  • Cloud Engineering - 6 years
  • Recommendation Systems - 3 years
  • AI Agents - 2 years

Preferred Environment

Python, Pandas, Linux, PyTorch, SQL, Artificial Intelligence (AI), Google Cloud Platform (GCP), Azure, AI Agents, AI Model Training

The most amazing...

...projects I've worked on were an end-to-end Agentic AI Sales Assistant and DL recommendation system to rank fashion eCommerce products.

Work Experience

Senior AI Engineer and Cloud Architect

2024 - PRESENT
Outdoor Living Supply - Main
  • Developed an AI agent connected to company sources and databases to assist sales and business teams with product recommendations, information, and overall business insights, combining structured data with natural conversational flow.
  • Designed, architected, and deployed the cloud architecture in Azure with microservices and observability.
  • Delivered a retrieval augmented generation and agent capabilities system capable of dealing with multimodal data and file formats from PDFs to images, videos, etc.
Technologies: Python, Generative Artificial Intelligence (GenAI), Full-stack Development, Large Language Models (LLMs), Cloud, Machine Learning, Azure, LangChain, Vector Databases, Google Cloud Platform (GCP), Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), Azure OpenAI Service, Vertex AI, Anthropic, Speech Recognition, Solution Architecture, Vector Search, Agentic Frameworks, Azure Blob Storage, Azure Cognitive Search, Retail Technology, Snowflake, API Integration, Amazon S3 (AWS S3), Cloud Platforms, Claude, Workflow Automation & System Integration, Workflow Automation, Flask, Agentic Coding, Azure AI Services, LLM Integration, Azure Service Fabric, Microsoft AI, Azure AI Studio, AWS Bedrock AgentCore

Senior ML Engineer

2022 - 2024
Flinks
  • Designed and developed ML systems to meet stakeholders' requirements and strategic business goals for solving payments and open banking. Designed and built ML systems to mitigate fraud risks in the payment sector.
  • Developed systems using OpenAI LLM capabilities to improve transactional data enrichment, ensuring robustness. Designed and deployed scalable ML systems using cloud resources on GCP and AWS.
  • Architected a system to improve web scraping automation using ML and computer vision models.
Technologies: Deep Learning, Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), Machine Learning, Google Cloud Platform (GCP), Python, PyTorch, Linux, Pandas, NumPy, SQL, Programming, Microsoft Power BI, Artificial Intelligence (AI), Data Scientist, Explainable Artificial Intelligence (XAI), Recurrent Neural Networks (RNNs), Time Series, Data Science, Transformer Models, Data Visualization, Data Engineering, Data Analytics, Data Interpretation, Data Analysis, Forecasting, Data Build Tool (dbt), Jupyter, Large Language Models (LLMs), Supervised Learning, Generative Artificial Intelligence (GenAI), Statistical Analysis, Regression Modeling, PostgreSQL, Data Modeling, Algorithms, Hierarchical Clustering, Clustering Algorithms, Clustering, K-means Clustering, Unstructured Data Analysis, Ollama, Amazon Web Services (AWS), Open-source LLMs, LangChain, OpenAI GPT-4 API, Keras, Rapid Prototyping, OpenAI API, GitHub, Architecture, Gemini, Prompt Engineering, Retrieval-augmented Generation (RAG), Meta Llama, Machine Learning Operations (MLOps), Large Language Model Operations (LLMOps), Computer Vision, Document Databases, NoSQL, Leadership, Cloud, Azure OpenAI Service, Vector Databases, Vertex AI, Anthropic, OpenAI, Web Scraping, Google Cloud, GitOps, Kubernetes, APIs, Big Data, Docker, Data Engineering, Data Pipelines, ETL, Data Wrangling, SQL, Data Visualization, Python, Artificial Intelligence (AI), Cloud, Data Analysis, Machine Learning, Google Cloud Platform (GCP), Amazon Web Services (AWS), FastAPI, Cloud Architecture, API Architecture, Apache Airflow, Data Pipelines, Data Cleansing, Amazon SageMaker, Deep Neural Networks (DNNs), Jupyter Notebook, NLU, AI Agents, AI Model Training, Agile Software Development, Technical Leadership, Algorithm Design, Hugging Face, Full-stack Development, Software Architecture, Cloud Engineering, Google Cloud Architecture Framework, Agentic AI, Automation, MoviePy, ElevenLabs Solutions, Distributed Cloud, Containerization, Fine-tuning, DeepSeek, Backtesting, Time Series Forecasting, Chatbots, Speech-to-Text (STT), AI Chatbots, REST APIs, Text Analytics, Text Classification, Word Embedding, Topic Modeling, Fintech, LangGraph, Semantics, Solution Architecture, Vector Search, Sales Forecasting, Demand Forecasting, Trend Forecasting, Image Processing, Agentic Frameworks, API Integration, Amazon S3 (AWS S3), Cloud Platforms, Workflow Automation & System Integration, Workflow Automation, Azure AI Services, LLM Integration

Senior Data Scientist

2021 - 2022
Farfetch
  • Led the data science development of data-driven initiatives and recommendation systems toward company strategic goals, such as increasing profitability and user engagement, while collaborating closely with product and engineering teams.
  • Delivered multiple data analyses to better understand customers, products, and their relations. Supplied multiple POCs to provide better clarity on commercial and fashion requirements.
  • Implemented deep learning models for information retrieval by extracting good representations from product images, product descriptions, user interactions, and other parameters.
  • Monitored live systems, fixed bugs, and implemented production-level features to current systems tested and released on production.
Technologies: Computer Vision, Deep Learning, PySpark, Machine Learning, Recommendation Systems, Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), QA Testing, Azure, Python, PyTorch, Linux, Pandas, NumPy, SQL, Programming, Statistics, Artificial Intelligence (AI), Data Scientist, Explainable Artificial Intelligence (XAI), Recurrent Neural Networks (RNNs), eCommerce, Time Series, Data Science, Transformer Models, Time Series Analysis, Data Visualization, Data Engineering, Data Analytics, Data Interpretation, Data Analysis, Forecasting, Jupyter, Large Language Models (LLMs), Supervised Learning, Generative Artificial Intelligence (GenAI), Statistical Analysis, Regression Modeling, Data Modeling, Algorithms, DBSCAN, Hierarchical Clustering, Clustering Algorithms, Clustering, K-means Clustering, Unstructured Data Analysis, Keras, A/B Testing, Rapid Prototyping, GitHub, Architecture, Machine Learning Operations (MLOps), Optimization Algorithms, AI-enabled Search, Cloud, Vector Databases, Spark, APIs, Big Data, Docker, Data Engineering, Data Pipelines, ETL, Data Wrangling, SQL, Data Visualization, Python, Artificial Intelligence (AI), Azure, Cloud, Data Analysis, Machine Learning, FastAPI, Cloud Architecture, API Architecture, Apache Airflow, Data Pipelines, Data Cleansing, Deep Neural Networks (DNNs), Jupyter Notebook, NLU, AI Model Training, Agile Software Development, Technical Leadership, Hugging Face, Software Architecture, Cloud Engineering, Automation, Distributed Cloud, Containerization, Fine-tuning, Backtesting, Time Series Forecasting, Streamlit, REST APIs, Text Analytics, Text Classification, Word Embedding, Semantics, Collaborative Filtering, Solution Architecture, Vector Search, Sales Forecasting, Demand Forecasting, Inventory, Trend Forecasting, Image Processing, Azure Blob Storage, Retail Technology, API Integration, Amazon S3 (AWS S3), Cloud Platforms, Azure AI Services

Head of AI | Senior Data Scientist

2018 - 2021
J!Quant
  • Delivered more than five strategic data science projects as a principal contributor, from conception to all phases of development and delivery.
  • Drove research roadmaps to deliver state-of-the-art (SOTA) solutions and build AI products. All AI products that I created are based on computer vision, NLP, time-series forecasting, and multi-modal representation learning.
  • Built a data science team, which included recruiting, teaching, and mentoring new data scientists. Taught data science to teams in different companies and individual professionals.
  • Assessed different companies' data-driven opportunities, making commercial proposals and selling data science projects to big companies.
Technologies: Computer Vision, Deep Learning, Machine Learning, SQL, Microsoft Power BI, Python, PyTorch, Linux, Pandas, NumPy, Programming, Statistics, TensorFlow, Optical Character Recognition (OCR), Data Scientist, Explainable Artificial Intelligence (XAI), Recurrent Neural Networks (RNNs), Time Series, Data Science, Transformer Models, Time Series Analysis, Data Visualization, Data Analytics, Supply Chain Management (SCM), Inventory Management, Data Interpretation, Data Analysis, Forecasting, Jupyter, Supervised Learning, Reinforcement Learning, Statistical Analysis, Regression Modeling, PostgreSQL, Data Modeling, Artificial Intelligence (AI), Algorithms, DBSCAN, Hierarchical Clustering, Clustering Algorithms, Clustering, K-means Clustering, Natural Language Processing (NLP), Unstructured Data Analysis, Amazon Web Services (AWS), Graph Databases, Neo4j, Keras, Rapid Prototyping, GitHub, Architecture, Demand Planning, AI Consulting, Optimization Algorithms, Logistics, Azure, Document Databases, AI-enabled Search, Leadership, Cloud, Vector Databases, icr, Geospatial Data, APIs, Docker, Supply Chain, Data Engineering, Data Pipelines, ETL, Data Wrangling, SQL, Data Visualization, Python, Artificial Intelligence (AI), Azure, Cloud, Data Analysis, Machine Learning, Amazon Web Services (AWS), FastAPI, Cloud Architecture, API Architecture, Data Cleansing, Deep Neural Networks (DNNs), Jupyter Notebook, NLU, AI Model Training, Agile Software Development, Technical Leadership, Algorithm Design, Hugging Face, Google Cloud Architecture Framework, Automation, MoviePy, Containerization, Fine-tuning, Backtesting, Time Series Forecasting, Speech-to-Text (STT), REST APIs, Text Analytics, Text Classification, Word Embedding, Topic Modeling, Semantics, Speech Recognition, Solution Architecture, Vector Search, Sales Forecasting, Demand Forecasting, Inventory, Trend Forecasting, Image Processing, Azure Blob Storage, Retail Technology, API Integration, Cloud Platforms, Flask

Research Intern

2017 - 2018
Werkzeugmaschinenlabor WZL der RWTH Aachen
  • Created programming solutions to analyze manufacturing data, signal processing, drive insights, and develop systems to improve production quality.
  • Developed two industrial research consulting projects to improve the quality and efficiency of hobbing and milling processes.
  • Built analytical, geometric, and statistical models to simulate industrial processes.
Technologies: MATLAB, Machine Learning, Simulations, Fourier Analysis, Python, Programming, Statistics, Supervised Learning, Statistical Analysis, Regression Modeling, Python

Experience

Multi Agent for AI Data Analyst, Sales Assistant, and Company Chatbot

A multi-agent system connected with databases and internal documents, capable of analyzing data and internal documents (PDFs, videos, images) and answering questions in a structured way, displaying data, product cards, and other information in a human-friendly manner. I ensured it was capable of recommending and retrieving relevant products for each user's intention and needs, as well as increasing basket size.

Personalized Ranking System for Two-sided Marketplace

A ranking system for one of the world's largest luxury marketplaces. While developing this ranking system, I considered multi-modal data, multiple business requirements, and relevance to each user to improve conversion, profitability, and other target metrics.

Gold Medal at the International Forecast Competition

https://www.kaggle.com/c/m5-forecasting-uncertainty
In 2020, I competed in one of the largest international forecasting competitions, the M5 competition. I won a gold medal for 7th place among 900+ teams worldwide.

The competition task was to forecast a daily demand distribution in quantiles for each Walmart product and three Walmart stores. This was a combination of over 40,000 time series.

Since I wanted to make our solution more general and practical and turn it into a product, I developed a unique end-to-end deep learning model based on recent advances in transformers for time-series forecasting instead of multiple ensembles or other unsuitable models for production approaches. It was the only model in the top 10 not using competition hacks.

Self-supervised Computer Vision Model for Fashion

Developed a new approach to extract image information from products for a big fashion marketplace. Leveraging the amount of data and self-supervised techniques, we could reduce human bias and capture rich features as texture improved other downstream systems.

SenseAI | Predicting and Monitoring Beer Quality for the World's Largest Brewery

A machine learning system to monitor beer quality during and after production. We perform the ETL process of thousands of industrial sensor signals using SQL. Also, we deploy machine learning models to predict the quality of the beer in real time and identify correlated root causes for production problems or improvements.

Our system also performs simulations, giving real-time visibility to the brewers and a way to act in real time during the process and improve product quality. It was deployed in the Azure/Databricks environment. The project was deployed in Brazilian breweries and mainly impacted the improvement of beer quality and waste reduction, saving over $1 million per year.

AI-powered Gift Recommendations

A smart giftee recommendation app based on occasion and questionnaire. As an AI engineer, I leveraged ChatGPT capabilities, Amazon web scraping, data science, and system design patterns to recommend a set of diverse and relevant products to users.

Education

2014 - 2019

Bachelor's Degree in Mechanical Engineering

Aeronautics Institute of Technology - São José dos Campos, São Paulo, Brazil

2018 - 2018

Progress Toward Master's Degree in Deep Learning and Machine Learning

RWTH Aachen University - Aachen, Germany

Certifications

MARCH 2019 - PRESENT

Deep Learning Specialization

Deep Learning.AI | via Coursera

Skills

Libraries/APIs

Pandas, PyTorch, Scikit-learn, Keras, OpenAI API, REST APIs, NumPy, TensorFlow, PySpark, MoviePy

Tools

Jupyter, GitHub, Apache Airflow, Algorithm Design, Claude, Microsoft AI, Microsoft Power BI, Azure OpenAI Service, Amazon SageMaker, MATLAB, DeepSeek

Languages

Python, SQL, C, Snowflake

Frameworks

Streamlit, LangGraph, Agentic Frameworks, Spark, Flask, Django

Paradigms

Rapid Prototyping, API Architecture, Agile Software Development, Automation

Platforms

Azure, Amazon Web Services (AWS), Vertex AI, Docker, Jupyter Notebook, Linux, Google Cloud Platform (GCP), Ollama, Kubernetes, Azure Service Fabric, Azure AI Studio, Databricks

Storage

PostgreSQL, Google Cloud, Data Pipelines, Amazon S3 (AWS S3), Graph Databases, Document Databases, NoSQL, Neo4j

Other

Deep Learning, Computer Vision, Natural Language Processing (NLP), Machine Learning, Recommendation Systems, Convolutional Neural Networks (CNNs), Explainable Artificial Intelligence (XAI), Artificial Intelligence (AI), Data Scientist, Recurrent Neural Networks (RNNs), eCommerce, Time Series, Data Science, Transformer Models, Time Series Analysis, Data Visualization, Data Analytics, Inventory Management, Data Interpretation, Data Analysis, Forecasting, Large Language Models (LLMs), Supervised Learning, Generative Artificial Intelligence (GenAI), Statistical Analysis, Regression Modeling, Data Modeling, Algorithms, DBSCAN, Hierarchical Clustering, Clustering Algorithms, Clustering, K-means Clustering, Unstructured Data Analysis, LangChain, OpenAI GPT-4 API, A/B Testing, Architecture, Prompt Engineering, Demand Planning, AI Consulting, Machine Learning Operations (MLOps), Optimization Algorithms, AI-enabled Search, Leadership, Cloud, Vector Databases, OpenAI, icr, APIs, Supply Chain, Data Engineering, Data Pipelines, ETL, Data Wrangling, SQL, Data Visualization, Python, Artificial Intelligence (AI), Azure, Cloud, Data Analysis, Machine Learning, Google Cloud Platform (GCP), Amazon Web Services (AWS), FastAPI, Cloud Architecture, Data Cleansing, Deep Neural Networks (DNNs), Google Cloud Architecture Framework, Cloud Engineering, AI Agents, AI Model Training, Technical Leadership, Hugging Face, Software Architecture, Agentic AI, ElevenLabs Solutions, Distributed Cloud, Containerization, Fine-tuning, Backtesting, Time Series Forecasting, Chatbots, Speech-to-Text (STT), AI Chatbots, Text Analytics, Text Classification, Word Embedding, Fintech, Semantics, Collaborative Filtering, Solution Architecture, Vector Search, Sales Forecasting, Demand Forecasting, Inventory, Trend Forecasting, Image Processing, Azure Blob Storage, Retail Technology, API Integration, Cloud Platforms, Workflow Automation & System Integration, Workflow Automation, Agentic Coding, Azure AI Services, LLM Integration, AWS Bedrock AgentCore, Statistics, Sequence Models, Neural Networks, Self-supervised Learning, Generative Pre-trained Transformers (GPT), Optical Character Recognition (OCR), Data Engineering, Supply Chain Management (SCM), Data Build Tool (dbt), Reinforcement Learning, Open-source LLMs, Gemini, Retrieval-augmented Generation (RAG), Meta Llama, Large Language Model Operations (LLMOps), Logistics, Anthropic, Web Scraping, Geospatial Data, GitOps, Big Data, NLU, Full-stack Development, Topic Modeling, Speech Recognition, Azure Cognitive Search, Programming, Simulations, QA Testing, Fourier Analysis, Path Optimization, Semantic Kernel (SK)

Collaboration That Works

How to Work with Toptal

Toptal matches you directly with global industry experts from our network in hours—not weeks or months.

1

Share your needs

Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2

Choose your talent

Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3

Start your risk-free talent trial

Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.

Top talent is in high demand.

Start hiring