Pavlo Karalupov, Developer in Vancouver, BC, Canada
Pavlo is available for hire
Hire Pavlo

Pavlo Karalupov

Verified Expert  in Engineering

AI Engineer and Developer

Location
Vancouver, BC, Canada
Toptal Member Since
April 16, 2021

Pavlo is a full-stack developer with six years of experience. This includes a software development internship at Amazon Web Services, focused on Amazon Transcribe, a deep-learning, text-to-speech application; a machine learning internship at Swisscom TV, focused on code-switching; and several small startups, including one that has over 2.5 million users across 250 hospitals. Pavlo's industry experience is backed by a master's degree in computer science focused on machine learning.

Portfolio

Microsoft
C++, Distributed Systems, Databases
Swisscom
Python, Kaldi, Bash, Speech to Text, Docker, Kubernetes, Machine Learning, Linux
Amazon Web Services (AWS)
Python, TensorFlow, Speech Analytics, Deep Neural Networks, PyCharm...

Experience

Availability

Part-time

Preferred Environment

Visual Studio, Visual Studio Code (VS Code), Bitbucket, Jira, Confluence

The most amazing...

...experience I've had was as a core developer in a four-person startup that grew to 2.5 million+ users in the Ukrainian medical market.

Work Experience

Software Engineer

2022 - PRESENT
Microsoft
  • Developed a database engine to work on petabytes of data.
  • Reviewed other team members' code and wrote different types of tests.
  • Took part in creating the feature roadmap and clarifying business requirements.
Technologies: C++, Distributed Systems, Databases

Research Scientist Intern

2020 - 2021
Swisscom
  • Improved a multilingual, automatic speech recognition (ASR) system for code-switching scenarios in Swisscom TV Voice Assistant by 10%.
  • Built a Docker and Kubernetes pipeline for training.
  • Set up data crawling for code-switch training of a language model.
Technologies: Python, Kaldi, Bash, Speech to Text, Docker, Kubernetes, Machine Learning, Linux

Software Development Engineer Intern

2019 - 2020
Amazon Web Services (AWS)
  • Developed a deep neural network for a speech segmenter using TensorFlow.
  • Created and optimized a deep neural network training pipeline with 3,000+ hours of speech recordings.
  • Improved a speech segmenter that was deployed to increase transcription quality for millions of Amazon Transcribe users.
Technologies: Python, TensorFlow, Speech Analytics, Deep Neural Networks, PyCharm, Code Review, Machine Learning, Linux, Amazon Web Services (AWS)

Lead Software Engineer

2019 - 2020
Triphub
  • Developed a microservice web app with JWT authentication and authorization.
  • Set up a CI workflow and a version control flow in Bitbucket.
  • Implemented fuzzy full-text search using Elasticsearch.
  • Created the back-end and front-end architecture from scratch.
  • Led a team of two developers, which included performing code reviews and assigning tasks.
Technologies: C#, ASP.NET Core, Elasticsearch, PostgreSQL, TypeScript, Vue, Identity Server, Nuxt.js, SignalR, .NET, LINQ, CSS, HTML, Microsoft Visual Studio, Visual Studio Code (VS Code), Code Review, Architecture, JSON, JSON Web Tokens (JWT), Software Architecture, Back-end, Front-end, Microservices, Azure, C#.NET, APIs, SQL, Travel, HTML5, REST, Full-stack, REST APIs, .NET Core, Leadership, Unit Testing, Integration Testing, Azure Blobs, Vuex, Vuetify, ASP.NET Web API, ASP.NET, Web API

Software Engineer

2016 - 2018
IT4Medicine
  • Developed a web application from scratch, which now has 2.5 million users.
  • Identified and optimized the most common and slow SQL queries, which saved 30% of the computational budget.
  • Set up CI/CD which allowed the business to scale painlessly to more than 250 hospitals.
  • Wrote unit and integration tests that decreased regression testing time from two weeks to several days.
  • Integrated an API that deals with push notifications and email campaign providers.
Technologies: C#, ASP.NET, Entity Framework, HTML, CSS, TypeScript, Angular, SignalR, .NET, LINQ, Microsoft SQL Server, Code Review, Microsoft Visual Studio, Architecture, JSON, Software Architecture, Back-end, Front-end, C#.NET, APIs, SQL, Bootstrap, Healthcare, HTML5, REST, Full-stack, REST APIs, Unit Testing, Integration Testing, ASP.NET Web API

Software Engineer

2016 - 2016
Radacode
  • Integrated protocols of five banks into the payment system to increase user coverage.
  • Improved authentication and authorization flows from access tokens to refresh tokens.
  • Tracked and fixed bugs, using Jira as a reporting tool.
Technologies: C#, ASP.NET MVC, JavaScript, .NET, LINQ, Microsoft SQL Server, API Integration, CSS, HTML, Code Review, Microsoft Visual Studio, JSON, Entity Framework, Razor, C#.NET, APIs, SQL, Financial Systems, HTML5, REST, Full-stack, REST APIs, Fintech, Unit Testing, ASP.NET Web API

Medical CRM (PB4)

A web application, created from scratch for Ukrainian medical reform, that allows patients to make appointments with doctors from home and monitor clinic activity.

I developed this application using HTML, CSS, JavaScript (AngularJS), TypeScript, Microsoft SQL, and C# (ASP.NET and Entity Framework). With this app, I won several hackathons and it now has over 2.5 million active users.

Amazon Transcribe

https://aws.amazon.com/transcribe/
Amazon Transcribe makes it easy for developers to add speech-to-text capabilities to their applications. Audio data is virtually impossible for computers to search and analyze. Therefore, recorded speech needs to be converted to text before it can be used in applications. Historically, customers had to work with transcription providers that required them to sign expensive contracts and were hard to integrate into their technology stacks to accomplish this task. Many of these providers use outdated technology that does not adapt well to different scenarios, such as low-fidelity phone audio that's common in contact centers, and this results in poor accuracy.

Amazon Transcribe uses a deep learning process, called automatic speech recognition (ASR), to convert speech to text quickly and accurately. Amazon Transcribe can be used to transcribe customer service calls, automate subtitling, and generate metadata for media assets to create a fully searchable archive.

Swisscom TV Voice Assistant

https://www.swisscom.ch/en/residential/help/device/blue-tv/voice-assistant.html
Voice control allows you to operate the Swisscom TV-Box with your voice. Swiss people usually speak more than one language fluently and, if needed, can switch easily between them—even in the same sentence. This phenomenon is called code-switching in the field of speech recognition.

The same phenomenon can be seen in the Swisscom TV Voice Assistant. In that scenario, the user might switch between languages when searching for a foreign actor; for example, "Find me a movie with Gérard Depardieu," where the intent is spoken in English and the entity is spoken in French.

After investigating different approaches for code-switching and multilingual speech recognition, I improved the system's word-error rate by 10% in code-switching scenarios.

PayPong

https://paypong.ua/
PayPong is the progressive, online, instant financial services platform for those who are active and enjoy life. It offers a quick and convenient solution for financial needs, such as:
• Money transfers from card to card and by bank details.
• Payment for telephone, internet, utility, and many other services.
• Getting an online loan in 15 minutes, credited directly to your bank card.
• Factoring and leasing.

Stockscore

A financial web application for browsing and assessing the risk of buying a particular stock.

I identified my customer's needs and requirements, selected the tech stack, implemented the system from scratch, wrote unit and integration tests, and configured the testing and deployment pipeline.

Wellet

Ticket sales applications for the Latin American region that used several payment providers as well as several payment methods (cash, card, partner seller, and more).

I was responsible for application enhancement on the back-end side such as the customer reservation profile to perform various actions with tickets, integration with more providers, ticket check-in, creating the recurring back-end tasks with the dashboard, among others.
2018 - 2021

Master's Degree in Computer Science

Swiss Federal Institute of Technology Lausanne (EPFL) - Lausanne, Switzerland

2014 - 2018

Bachelor's Degree in Computer Engineering

Taras Shevchenko National University of Kyiv - Kyiv, Ukraine

Libraries/APIs

Entity Framework, Vue, LINQ, REST APIs, Vuex, PyTorch, SignalR, TensorFlow, OpenCV, Web API

Tools

Kaldi, Visual Studio, Bitbucket, Jira, Confluence, Microsoft Visual Studio, PyCharm, Dapper, Hangfire, Whisper

Frameworks

ASP.NET Core, ASP.NET, .NET, JSON Web Tokens (JWT), .NET Core, ASP.NET Web API, ASP.NET MVC, Angular, Nuxt.js, Razor, Bootstrap, Vuetify, Entity Framework Core, FluentMigrator

Paradigms

Object-oriented Programming (OOP), Microservices, REST, Unit Testing

Languages

C#, HTML, CSS, Python, C#.NET, TypeScript, JavaScript, SQL, Bash, HTML5, C++

Storage

JSON, Elasticsearch, PostgreSQL, Microsoft SQL Server, Azure Blobs, MySQL, Databases

Platforms

Azure, Visual Studio Code (VS Code), Docker, Kubernetes, Linux, Arduino, Raspberry Pi, Amazon Web Services (AWS)

Industry Expertise

Healthcare

Other

API Integration, Back-end, APIs, Full-stack, Machine Learning, Deep Neural Networks, Code Review, Architecture, Software Architecture, Front-end, Speech to Text, Data Analysis, Identity Server, Speech Analytics, Natural Language Processing (NLP), Computer Vision, Image Processing, Finance, Travel, Financial Systems, Leadership, Fintech, Object Detection, Image Recognition, Integration Testing, Distributed Systems, GPT, Generative Pre-trained Transformers (GPT)

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