Nestor Yuri Sanchez Guadarrama, Developer in Edinburgh, United Kingdom
Nestor is available for hire
Hire Nestor

Nestor Yuri Sanchez Guadarrama

Verified Expert  in Engineering

Data Scientist and Software Developer

Edinburgh, United Kingdom

Toptal member since March 23, 2022

Bio

Nestor has a solid academic background in machine learning and industry experience as a software engineer and data scientist. He built a production-level Python package for power system adequacy modeling used by researchers at the Alan Turing Institute, a GCP-based end-to-end ML pipeline for generative deep learning models, and ML-based products to understand the impact of PR campaigns. Nestor enjoys staying up-to-date with the latest technologies in the data science and MLOps spaces.

Portfolio

Lynceus
Amazon Web Services (AWS), Python, Linux, Amazon SageMaker, Terraform...
Cellsight
Python, Bash, SQL, Python 3
The Alan Turing Institue
Python, C, Statistics, Pandas, NumPy, RStudio, Project Management

Experience

  • Statistics - 10 years
  • Machine Learning - 8 years
  • Python - 7 years
  • Software Engineering - 7 years
  • R - 7 years
  • Linux - 7 years
  • Research - 4 years
  • Google Cloud Platform (GCP) - 2 years

Availability

Part-time

Preferred Environment

Linux, Python, Google Cloud Platform (GCP), R

The most amazing...

...model I have worked on enabled a 4% throughput increase in a high-value production process.

Work Experience

Senior Machine Learning Engineer

2023 - PRESENT
Lynceus
  • Designed and deployed a production RAG system on AWS, which provides live assistance to process and maintenance engineers.
  • Redesigned and maintained the company’s main proprietary machine learning library, specializing in semiconductor manufacturing applications.
  • Mentored data scientists and established coding standards across projects.
  • Developed models for smart quality control in specific manufacturing processes, reducing sampling by up to 25% without degrading quality metrics.
Technologies: Amazon Web Services (AWS), Python, Linux, Amazon SageMaker, Terraform, Scikit-learn, Machine Learning, Machine Learning Operations (MLOps), MLflow, Large Language Models (LLMs)

Back-end Engineer

2022 - PRESENT
Cellsight
  • Maintained the back-end codebase and ETL pipelines continuously using Python and Bash.
  • Implemented new features and optimized ETL pipelines.
  • Created documentation for the legacy codebase and swapped out old or deprecated libraries.
Technologies: Python, Bash, SQL, Python 3

Research Software Engineering Consultant

2022 - 2022
The Alan Turing Institue
  • Produced a production-level Python package for power system adequacy modeling intended to be used by researchers on projects outside the scope of my Ph.D.
  • Engaged with researchers to familiarize them with the package functionality.
  • Collaborated on developing a decision support system for risk management and capacity procurement in the context of Great Britain's power system.
Technologies: Python, C, Statistics, Pandas, NumPy, RStudio, Project Management

Academic Consultant

2021 - 2021
National Grid
  • Produced an analysis of near-term security of supply risks for the power grid under different future scenarios.
  • Engaged with stakeholders and other academic consultants to understand their needs in terms of software and modeling.
  • Produced a solid codebase and ensured a solid and reproducible analysis through good engineering practices.
Technologies: R, Data Science, Statistics, Data Visualization, RStudio

ML Engineering Consultant

2018 - 2018
Wella Online
  • Prototyped a new data service in the form of an ML-based student failure prediction pipeline.
  • Engaged with the client and product teams frequently to incorporate their feedback into the project.
  • Deployed on AWS as a RESTful API using Python's Falcon and a MongoDB back end.
Technologies: Python, MongoDB, Amazon Web Services (AWS), Data Science, Machine Learning, Pandas, NumPy, Scikit-learn, Project Management, Python 3

Software Developer

2015 - 2017
Sinnia
  • Quantified the impact of marketing campaigns using network models and NLP.
  • Created ML models for demographic feature inference of Twitter users.
  • Collaborated directly with clients to design ML-backed dashboards for real-time audience segmentation.
Technologies: Python, R, Spark, Scala, Amazon Web Services (AWS), Bash, Data Science, Statistical Data Analysis, Statistics, Machine Learning, Data Visualization, Data Analysis, Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), Data Analytics, Scikit-learn, RStudio, RStudio Shiny, Project Management, Data Extraction, Python 3, SQL

Data Scientist

2015 - 2015
Mimoni
  • Tested statistical hypotheses to better understand the customers.
  • Produced the methodology for a weekly KPI forecast report intended for executive-level management.
  • Assisted in improving the quality of credit scoring models.
Technologies: R, Data Science, Statistical Data Analysis, Statistics, Machine Learning, Data Visualization, Data Analysis, Data Analytics

Experience

Generative Models for Typefaces

https://github.com/nestorSag/textfont-ai
A Python package implementing a GCP-based end-to-end machine learning pipeline for generative deep learning models using Typeface data. It uses Beam for data preprocessing, TensorFlow for model training, and MLFlow for experiment tracking.

Production-level Code for Power System Adequacy Modeling

https://github.com/nestorSag/riskmodels
A Python package implementing parametric extreme value models and optimized functionality for power system adequacy assessment. The package will be used by researchers at the Alan Turing Institute for various projects involving energy adequacy risks for future climate scenarios.

Bootstrapping a Kubernetes Cluster on EC2 from Scratch

https://github.com/nestorSag/auto-k8-cluster
This repository uses GNU Make, Ansible, Terraform, and Python to bootstrap a highly available Kubernetes cluster on EC2 from the ground up. It is meant as a testing ground for some DevOps technologies.

Education

2019 - 2022

Ph.D. in Statistics

University of Edinburgh - Edinburgh, UK

2018 - 2019

Master's Degree in High Performance Computing

University of Edinburgh - Edinburgh, Scotland

2010 - 2014

Bachelor's Degree in Informatics and Applied Mathematics

Mexico Autonomous Institute of Technology - Mexico City, Mexico

Certifications

OCTOBER 2020 - PRESENT

Professional Data Engineer

Google Cloud

JULY 2017 - PRESENT

Structuring Machine Learning Projects

Coursera

Skills

Libraries/APIs

Pandas, NumPy, Scikit-learn, TensorFlow

Tools

Apache Beam, Ansible, Terraform, GNU Make, Amazon SageMaker

Languages

Python, R, SQL, Python 3, Bash, C, Scala

Platforms

RStudio, Linux, Google Cloud Platform (GCP), Kubernetes, Amazon Web Services (AWS)

Industry Expertise

Project Management

Frameworks

RStudio Shiny, Spark

Paradigms

Parallel Programming, CRISP-DM

Storage

MongoDB

Other

Statistics, Mathematics, Machine Learning, Data Visualization, Data Science, Statistical Data Analysis, Data Analysis, Data Analytics, Data Extraction, Research, Software Engineering, Natural Language Processing (NLP), Time Series Analysis, Forecasting, Generative Pre-trained Transformers (GPT), IT Project Management, Distributed Systems, Big Data, Big Data Architecture, Cloud Computing, Data Engineering, Machine Learning Operations (MLOps), MLflow, Large Language Models (LLMs)

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