Verified Expert in Engineering
Machine Learning Developer
Formerly a data science lead and entrepreneur in the climate tech industry, Nathan is an expert in applied AI and geospatial intelligence in diverse spaces such as Earth Observation, 3D reconstruction, customer behavior prediction, or natural language understanding. He can support with full-stack development of AI and geospatial tools.
SQL, Python, Google Cloud, React, Mapbox GL, PyTorch, GitHub
The most amazing...
...thing I did was start my own solar software company building a geospatial MVP from scratch on a Django, React, and Mapbox stack.
- Developed and supervised the development of an MVP for a geospatial tool gathering 20+ datasets in a lead generation interface for solar developers.
- Established the business plan and product roadmap for a VC-backed B2B SaaS company.
- Pitched the solution to hundreds of investors and customers, either in front of large audiences or through direct outreach efforts.
- Designed and implemented the investor and sales pitches.
Technical Program Manager
- Brought the primary project from its concept documentation to the delivery of photorealistic 3D reconstruction for self-driving car AI training (Waymo) at the city scale.
- Technical implementation and design of an AI-powered texturing engine for the 3D reconstruction of buildings.
- Launched and operated 2D / 3D data creation pipelines for ML training, leading to multiple Maps improvements.
Lead Product Analyst, Geo Imagery Ops
- Implemented ML pilot projects for 5x time gain on bike lane mapping in new countries.
- Led the development and maintenance of a pool of 80+ dashboards and ETLs used by the management of a 500-people Ops organization.
- Redefined the resource allocation model for StreetView driving, leading to a 14% gain in driving efficiency in global operations.
- Organized collaboration with the City Council and university (UCD), leading to the integration of Google's emissions data in the city's climate action planning.
Data Science Fellow
- Created end-to-end NLP pipeline with Spark and Doc2Vec to detect sensitive content in movie subtitles and classify movies accordingly.
- Implemented with Frequentist and Bayesian frameworks for A/B Testing and applied to numerous use cases.
- Detected fraud in a large dataset of transaction data and built a monitoring dashboard using Flask / MongoDB / Matplotlib.
- Analyzed, visualized, and predicted churn likelihood in transportation data from a ride-sharing app using Gradient Boosted Trees, SVMs, Random Forests, and ensembling techniques.
- Built a recommendation engine based on joke-like data from the Jester dataset using matrix factorization and collaborative filtering techniques.
Data Science Consultant
- Detected fraud in car insurance claims by implementing random walks on bipartite graphs.
- Predicted the price of car parts leveraging recommender systems on car insurance audit data.
- Implemented web scraper to collect several million entries for a movies/actors/productions database.
Business Intelligence Manager
- Led the business intelligence department and its business analyst team for a 1 million-member startup.
- Ensured data quality and information access by building dashboards and data pipelines from various sources and designing the data warehouse. Used SQL, AWS S3/Redshift/DP, and Ruby on Rails.
- Accelerated daily newsletter generation time by a factor of 10 by initiating and supervising partial automation of the creation process.
- Automated bidirectional data flow between the internal data warehouse and external marketing partners using Python.
Junior Data Scientist
- Identified 70% of future buyers by building a neural network model on early days activity. R, SQL.
- Built and managed 100+ analytics dashboards and a custom interface for visualizing metrics. Used Ruby on Rails, NVD3.js, and SQL.
- Increased conversion rate by 20% for members in the disengagement phase through A/B Testing programs.
Visualization of Multimedia Datasetshttps://github.com/Nathx/d3_cartography
Built using D3.js, Paper.js, and Raphael.js.
Parental Advisory Machine Learning
Built using Python, Spark, Doc2Vec, Selenium, and Scrapy.
Data Science, Agile Software Development
PostgreSQL, Databases, Redshift, MongoDB, Amazon S3 (AWS S3), AWS Data Pipeline Service, Google Cloud, Google Cloud SQL
Machine Learning, Data Mining, Data Engineering, Geospatial Data, Computer Vision, Artificial Intelligence (AI), Image Processing, Data Analysis, Data Scientist, Dashboards, Reports, Data Analytics, Heatmaps, Web Scraping, Natural Language Processing (NLP), GPT, Generative Pre-trained Transformers (GPT), Full-stack, Google Cloud Machine Learning, Software Architecture, Data Visualization, Information Systems, Strategy, Technical Program Management, Business Development, Partnerships, New Products, Machine Learning Operations (MLOps), Prototyping, Mapping, Geospatial Analytics, Business to Business (B2B), Product Roadmaps, Product Development, Product Strategy, Sales, Fundraising, Augmented Reality (AR)
Apache Spark, Spark, Flask, GraphLab, Paper.js, Ruby on Rails (RoR), Django
Spark ML, React, Scikit-learn, NVD3, Raphaël, Matplotlib, D3.js, Mapbox GL, PyTorch
Google Analytics, GitHub, Atom, IPython, BigQuery, Tableau, Google Cloud AI, GIS
Amazon Web Services (AWS), Amazon EC2, Linux, Mapbox, Google Cloud Platform (GCP), MacOS, GIS Cloud
Certificate in Data Science
Galvanize - (via online at http://www.galvanize.com/)
Engineer's/Master's Combined Degree in Computer Science
École Centrale Paris - Paris, France
Bachelor's Degree in Physics & Engineering
Lycée et Collège LAKANAL - Sceaux, France