Darin Erat Sleiter, Developer in Florianópolis - State of Santa Catarina, Brazil
Darin is available for hire
Hire Darin

Darin Erat Sleiter

Verified Expert  in Engineering

Machine Learning Developer

Location
Florianópolis - State of Santa Catarina, Brazil
Toptal Member Since
October 11, 2016

Darin is a data scientist and engineer with a PhD in physics from Stanford. He's passionate about data and machine learning and has worked on data science projects across numerous industries and applications. Darin's co-founded an AI company and led a team of data scientists to build a product which uses machine learning and optimization techniques to reduce energy consumption in data centers. He's eagerly waiting for quantum computers.

Portfolio

Agency Enterprise Studio
Amazon Web Services (AWS), Pandas, Poetry, Pytest, Flask, Scikit-learn, SciPy...
Self Employed
Amazon Web Services (AWS), Kubernetes, Docker, Tesseract...
California Data Science
Keras, TensorFlow, Python, Neural Networks, Machine Learning, Data Science

Experience

Availability

Part-time

Preferred Environment

PyCharm, Sublime Text, Jupyter Notebook, Git, Ubuntu

The most amazing...

...product I've built combines machine learning with physics-based modeling to optimize energy usage within a data center.

Work Experience

Senior Data Scientist

2019 - PRESENT
Agency Enterprise Studio
  • Used computer vision to read and process the results of at-home wellness tests which improved algorithm performance by more than 190%.
  • Designed a complete strategy for image moderation of user-uploaded content for one client, and built an MVP implementation for a number of the components.
  • Implemented a computer vision algorithm for finding, deskewing, and cropping a client product within user-uploaded images.
Technologies: Amazon Web Services (AWS), Pandas, Poetry, Pytest, Flask, Scikit-learn, SciPy, Linux, Jupyter, Amazon SageMaker, OpenCV, Python

AI Developer | Data Scientist

2018 - 2019
Self Employed
  • Filled a role as interim CTO for an AI startup focused on processing medical and legal documents using computer vision and natural language processing.
  • Helped guide the company’s machine learning approach.
  • Taught development best practices and how to reduce technical debt to their development team.
  • Advised on how to comply with the technical requirements of HIPAA.
Technologies: Amazon Web Services (AWS), Kubernetes, Docker, Tesseract, Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), Python

Co-founder | Chief Data Scientist

2016 - 2018
California Data Science
  • Hired and led a team of data scientists to build AI products for the data center industry.
  • Built a product based on machine learning, simulation, and optimization which optimizes energy consumption by the cooling system of data centers.
  • Implemented predictive maintenance tools using machine learning.
  • Contributed to every part of the process of creating, operating, and growing a small startup.
Technologies: Keras, TensorFlow, Python, Neural Networks, Machine Learning, Data Science

Freelance Senior Python Developer with Machine Learning Experience

2016 - 2017
Bractlet (via Toptal)
  • Developed a Python application which uses machine learning to calibrate time-intensive physics-based energy models using the fewest number of simulations as possible.
Technologies: NumPy, Pandas, SciPy, Scikit-learn, Machine Learning, Python

Data Scientist

2016 - 2017
Youbeo, Inc.
  • Subcontracted on a variety of data science projects.
  • Worked with machine learning and predictive modeling.
  • Analyzed and processed Internet of Things sensor data.
  • Built analytics services deployed on AWS.
Technologies: Amazon Web Services (AWS), MongoDB, PostgreSQL, Git, Jupyter Notebook, Scikit-learn, Python

Freelance Data Science Consultant

2016 - 2017
Freelance Work
  • Helped small companies and startups take advantage of their data.
  • Created predictive models using machine learning.
  • Built web service-based data analytics products.
  • Analyzed IoT big data.
  • Worked with natural language processing with neural networks.
  • Wrote classification and regression algorithms.
  • Implemented time-series forecasting.
Technologies: Amazon Web Services (AWS), Linux, MongoDB, PostgreSQL, Git, Jupyter Notebook, TensorFlow, Scikit-learn, Python

Senior Data Scientist

2015 - 2016
Bravi Software
  • Used machine learning to build models predicting which university students are at risk of dropping out.
  • Designed and built composite scales to evaluate students across a number of dimensions.
  • Packaged the analytics platform inside a docker image accessible with a RESTful web API.
  • Helped guide and teach junior members on the data science team.
  • Worked closely with the design and software teams to ensure good integration with the analytics platform.
Technologies: Weka, Docker, MongoDB, Linux, Jupyter Notebook, Scikit-learn, Python

Software Developer

2012 - 2015
Way2 Technology
  • Built a highly parallel and asynchronous platform to collect data from energy meters across Brazil.
  • Developed the platform as a set of microservices using an actor-based design pattern.
  • Implemented drivers using a variety of communication protocols to communicate with energy meters.
  • Enforced clean code and unit testing practices to ensure quality software (working as a core member of the team).
  • Worked as a scrum master to enable and facilitate my team through Agile development practices.
Technologies: Asynchronous I/O, Octopus Deploy, TeamCity, Mercurial, SQL, Visual Studio, C#

Physics Ph.D. Candidate | Researcher

2006 - 2012
Stanford University
  • Performed experimental and theoretical research into quantum computation using solid-state physics and quantum optics.
  • Designed and executed experiments in the laboratory and analyzed the data results.
  • Performed numerical simulations of complex quantum systems.
  • Used maximum likelihood estimation and confidence intervals to determine quantum system parameters from experimental data.
  • Built software and a dashboard to control multiple pieces of hardware and collect data.
Technologies: LabWindows/CVI, FPGA, Java, C++, LabVIEW, MATLAB

Energy Model Calibration with Machine Learning

While working on a Toptal project for Bractlet (an award-winning company focused on modeling building energy usage in order to improve energy efficiency), I developed an application which uses machine learning to calibrate physics-based energy models.

These models are very powerful, but they take a long time to run and contain a number of parameters which must be calibrated and are not known ahead of time. Thus the objective of the application was to automate the calibration of these parameters using as few iterations of the physics-based model as possible.

For this project, I developed an application that uses machine learning to model the parameter space and select parameter sets to use in simulations, simultaneously exploring the parameter space and minimizing the physics-based model error without human input.

Student Predictive Analytics Platform

I worked with a team at Bravi to build a predictive model for a Brazilian university in order to indicate those students at risk of dropping out.

We cleaned and extracted features from the raw university data, evaluated the performance of various machine learning algorithms and the models they produced, and incorporated the resulting models into a Docker image which is currently in use at the university. The predictions are then used to focus early attention on students who are at risk of dropping out and maximize their chance of continuing their studies.

Predictive Model for Baseball Games

My first experience with machine learning was at the end of my undergrad time at Princeton when a friend approached me to help him implement a model to predict the outcome of baseball games, which he had designed as part of his senior thesis.

We used non-parametric statistics (before machine learning was a buzzword), and custom built a model to predict the probabilities of certain events occurring in a particular game. The model was a nearest neighbor's implementation using composite indices for dimensional reduction.

Treating baseball betting as a market, we used the model to trade very successfully for two years before new laws made the market unavailable.

Data Collection Platform for Energy Data

At Way2, I worked with an Agile team to build a platform to collect data from energy meters throughout Brazil and South America.

We designed and built a scalable microservice solution which is highly parallel and asynchronous, robust for longterm stability, can communicate using a variety of communication protocols, and has detailed logging.

This platform is currently in use by CCEE, the Brazilian government agency which manages the Brazilian energy market, collecting data from tens of thousands of meters.

Predictive Model for Bike Sharing System

The purpose of this repository is to show how I like to develop data science projects and what can be built in a few hours. It includes two Jupyter notebooks—the first showing exploratory analytics and discussion of the data, and the second showing the performance of predictive models built via machine learning.

The performance of some standard machine learning algorithms are compared to that of a custom-designed model tailored to the system being modeled. The custom model results in a reduction of nearly half the residual error between the prediction and the testing data.

Verbalist Android App

Verbalist was a productivity app for Android available on the Google Play App Store.

It was a list manager with voice-to-text and semi-structured language processing which allowed users to control the app and add list items by voice. The app had thousands of users and a 4.8 star rating until we stopped development.
2006 - 2012

Ph.D. in Physics

Stanford University - Stanford, CA, USA

2006 - 2011

Master's Degree in Physics

Stanford University - Stanford, CA, USA

2002 - 2006

Certificate of Proficiency in Engineering Physics

Princeton University - Princeton, NJ, USA

2002 - 2006

Certificate of Proficiency in Applied and Computational Mathematics

Princeton Univeristy - Princeton, NJ, USA

2002 - 2006

Certificate of Proficiency in Applications of Computer Science

Princeton Univeristy - Princeton, NJ, USA

2002 - 2006

Bachelor's Degree in Physics

Princeton Univeristy - Princeton, NJ, USA

Libraries/APIs

TensorFlow, Matplotlib, SciPy, Pandas, Scikit-learn, NumPy, Keras, React, OpenCV

Tools

Git, Jupyter, IPython, MATLAB, Mercurial, Sublime Text, PyCharm, Visual Studio, TeamCity, LabVIEW, LabWindows/CVI, Amazon SageMaker, Pytest, Mathematica, Weka

Languages

SQL, Python, C#, Swift, Go, PHP, Java, C++, C, JavaScript, HTML

Paradigms

Distributed Computing, Data Science, Unit Testing, Scrum, Clean Code, Parallel Computing, Agile Software Development, Asynchronous Programming, Automation, Continuous Delivery (CD), DevOps

Platforms

Windows, Linux, iOS, Docker, Ubuntu, Jupyter Notebook, Kubernetes, Amazon Web Services (AWS), Android

Storage

PostgreSQL, MySQL, MongoDB

Frameworks

Apache Spark, Flask

Other

Experimental Design, Data Engineering, Data Mining, Physics Simulations, Statistics, Neural Networks, Predictive Analytics, Machine Learning, Signal Processing, Scientific Computing, Predictive Modeling, Deep Learning, Quantum Computing, Time Series Analysis, Artificial Intelligence (AI), Freelancing, Data Analysis, Web Development, Data Modeling, Virtual Reality (VR), Software Development, Big Data, RESTful Web Services, Natural Language Processing (NLP), Convolutional Neural Networks (CNN), Genetic Algorithms, Prescriptive Analytics, Prescriptive Modeling, Reinforcement Learning, Generative Pre-trained Transformers (GPT), Octopus Deploy, Asynchronous I/O, FPGA, Poetry, Tesseract

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