George is available for hire

George Brova

Verified Expert in Engineering

AI Developer

Location

London, United Kingdom

Toptal Member Since

April 15, 2020

George is a pragmatic developer motivated by the challenge of solving hard problems. He is proficient across the stack, from publishing original academic research to prototyping real-world machine learning models, building distributed databases, and scaling NLP models. His work has improved airline demand forecasting accuracy, and optimized systems to save money and time. George champions good DevOps practices (fast tests, one-step deployment) and a deliberate culture of testing and clean code.

Machine Learning Git Unit Testing Python Docker MongoDB Python-rq Natural Language Processing (NLP)SQL Natural Language Toolkit (NLTK)REST APIs Java Microservices Amazon Web Services (AWS)gRPC

Portfolio

Migacore Technologies

Amazon Web Services (AWS), Redis, PostgreSQL, MongoDB, Google Cloud, Kubernetes...

Palantir Technologies

Amazon Web Services (AWS), Docker, Java

Experience

Python - 7 years Scikit-learn - 5 years Machine Learning - 5 years Java - 4 years Docker - 3 years MongoDB - 3 years TensorFlow - 2 years

Availability

Part-time

Preferred Environment

Slack, Visual Studio Code (VS Code), Linux

The most amazing...

...startup I've built is Migacore Technologies. I raised >$1 million in funding and improved airline demand forecasting accuracy by >4%.

Work Experience

CTO and Engineering Lead

2017 - PRESENT

Migacore Technologies

Utilized machine learning with engineering to design, build, and refine a system to (1) crawl and extract events worldwide, and (2) learn what types of events have the most impact on the demand for air travel.
Set up and maintained continuous deployment (CircleCI, Docker on GCP). Built tooling for fast distributed computing. Some of our experiments ran on up to 1000 CPUs.
Built, developed, and grew the machine learning and engineering teams. Managed a team of eight individual contributors.

Technologies: Amazon Web Services (AWS), Redis, PostgreSQL, MongoDB, Google Cloud, Kubernetes, Docker, Keras, Scikit-learn, Python

Software Engineer

2015 - 2016

Palantir Technologies

Built an internal deployability tool, which allows customers to describe their product stack in a custom DSL (Java, Groovy).
Developed AtlasDB, a transactional layer on top of a key-value store (Java, distributed system design).
Contributed to code review and testing best practices. Wrote one of the first Docker-based end-to-end tests at Palantir.

Technologies: Amazon Web Services (AWS), Docker, Java

Experience

Demandgraph by Migacore Technologies

A demand forecasting tool to help airlines estimate travel demand. Our model trained on many indicators, but our unique value add is (1) information about news and consumer sentiment, as well as (2) details about upcoming events such as major conferences or trade shows. This model helped Lufthansa Group increase its prediction accuracy by approximately 4%. I gave a joint talk about this with Tabea Hesler from Swiss Airlines at AMLD: https://www.youtube.com/watch?v=ezNGXojH-XI.

Skills

Languages

Python, SQL, Java, JavaScript, TypeScript, Go

Libraries/APIs

Python-rq, REST APIs, TensorFlow, Keras, Scikit-learn, Natural Language Toolkit (NLTK), SpaCy, Node.js

Tools

Gensim, Git, Slack

Paradigms

Unit Testing, Microservices, Concurrent Programming

Platforms

Docker, Kubernetes, Amazon Web Services (AWS), AWS Lambda, Linux, Visual Studio Code (VS Code)

Storage

MongoDB, Google Cloud, PostgreSQL, Redis, Cassandra, RDBMS

Other

APIs, Machine Learning, Image Processing, Natural Language Processing (NLP), GPT, Generative Pre-trained Transformers (GPT), Artificial Intelligence (AI), Back-end, Cloud, Serverless, Natural Language Understanding (NLU), Chatbots

Frameworks

gRPC, Django

Education

2012 - 2015

Ph.D. (Currently On Leave) in Computer Science

University of Illinois at Urbana-Champaign - Urbana, Illinois , USA

2008 - 2012

Master's Degree in Computer Science

Boston University - Boston, Massachusetts, USA

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.

Share your needs

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

Choose your talent

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

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