Elektra Papazoglou, Developer in London, United Kingdom
Elektra is available for hire
Hire Elektra

Elektra Papazoglou

Verified Expert  in Engineering

Deep Learning Developer

Location
London, United Kingdom
Toptal Member Since
January 9, 2020

Elektra has thorough hands-on experience in machine learning projects from conception to architecture design, model implementation, and final production in order to solve open-ended questions. She has worked closely with software engineers to build data platforms and products that would serve as the foundation of the data practices of the business. She has experience in the following industries: consulting, travel, and publishing.

Portfolio

Skyscanner
Amazon Web Services (AWS), Scala, SQL, Python, Spark, Databricks
Reach plc
Amazon Web Services (AWS), Drone CI, Docker, Spark, Scala, Python, TensorFlow...

Experience

Availability

Part-time

Preferred Environment

Amazon Web Services (AWS), IntelliJ IDEA, PyCharm, iOS

The most amazing...

...project I have worked on was an article recommendation engine that managed to bump CTR by 5% for a major UK news company in their digital division.

Work Experience

Data Scientist

2019 - PRESENT
Skyscanner
  • Achieved speed and cost optimizations on back-end systems and ticket price accuracy via ML models.
Technologies: Amazon Web Services (AWS), Scala, SQL, Python, Spark, Databricks

Data Scientist

2016 - 2019
Reach plc
  • Created an image processing model with TensorFlow to change the size and focal point of images so that they can be resized to fit smaller screens.
  • Created a complex recommendation engine based on three stages: content similarity, item-based collaborative filtering, and user-based collaborative filtering with Spark and Scala.
  • Created a deduplication pipeline to pick out new duplicate articles and score them with AWS and NLP.
  • Created an NLP engine that generates several different new labels for text data, by using ML and processing them in a streaming fashion with AWS, TensorFlow, and Python.
Technologies: Amazon Web Services (AWS), Drone CI, Docker, Spark, Scala, Python, TensorFlow, Deep Learning, Machine Learning, Elasticsearch

Data Scientist

2015 - 2016
Decision Technology
  • Worked as a data science and machine learning consultant on proof of concept projects for various clients in the gambling and legal sectors.
Technologies: Python

Data Scientist

2014 - 2015
First Group
  • Created reporting suite with SQL and statistical analysis to alert on outliers in order to manage ticket pricing for specific routes and dates.
Technologies: SQL, Python

Recommendation Engine System

Worked on a custom implementation of a real-time recommendation engine using AWS, Python, and Elasticsearch to serve article recommendations based on collaborative filtering.

NLP Engine

Created an NLP engine to process articles from a stream through various ML models (trained using Python and TensorFlow) and enrich them with metadata such as entities, categories, sentiment and tags about what products to advertise with a specific article. The articles were then stored into various databases and the engine was accessed via an API.

Image Auto-Cropper

Deployed model to automatically resize and zoom into images so that they can be adapted to fit smaller device screens. Runs as a docker API and is based on a TensorFlow model for image processing along with custom logic for post-processing.

Article deduplication pipeline

Created an AWS pipeline that checks new entries streamed through the system for near-duplicate text in the body of articles stored in a database. When part of the text is recognized as an existing item's duplicate, a score is assigned to it depending on the level of duplication, via NLP. The pipeline is currently used to optimize for SEO ratings by boosting the unique content generated on a website.

Determining Court Outcomes

Worked as a consultant on a Python-based proof of concept to model the likelihood that a particular case will be successful in trial, in order to consult over if and what settlement should be pursued for particular cases of commercial law.

Languages

Python, Scala, SQL

Frameworks

Spark

Storage

Elasticsearch

Other

Machine Learning, Computer Vision, Deep Learning, APIs

Libraries/APIs

TensorFlow

Platforms

Amazon Web Services (AWS), Drone CI, Docker, iOS, Databricks

Tools

PyCharm, IntelliJ IDEA

2015 - 2017

Master of Science Degree in Data Science

City University of London - London, England

2014 - 2015

Master of Science Degree in Management

Imperial College Business School - London, England

2013 - 2014

Master of Science Degree in Statistical Genetics

Imperial College - London, England

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