Sergey Nichiporchik, Developer in Minsk, Belarus
Sergey is available for hire
Hire Sergey

Sergey Nichiporchik

Verified Expert  in Engineering

Machine Learning Developer

Location
Minsk, Belarus
Toptal Member Since
December 25, 2019

Sergey is a data scientist with exemplary skills in software engineering. A solid background in machine learning and computer science allows him to develop solutions for business problems from scratch to production-ready state. Sergey's primary asset is his keen analytical abilities.

AlgorithmsNatural Language Processing (NLP)PythonFlaskGitTensorFlowMachine LearningDeep LearningComputer VisionLinuxC++CTest-driven Development (TDD)SQLKeras

Portfolio

Altoros
GIS, Kubernetes, Docker, Flask, FastAPI, Neo4j, Keras, TensorFlow, Python
Kreo Software
Amazon Web Services (AWS), MongoDB, React, Amazon Mechanical Turk, Neo4j, SpaCy...
Kinross Research
JavaScript, Django, Pandas, TensorFlow, Python

Experience

Python - 5 yearsTensorFlow - 4 yearsMachine Learning - 4 yearsDeep Learning - 4 yearsKeras - 4 yearsGPT - 4 yearsNatural Language Processing (NLP) - 4 yearsGenerative Pre-trained Transformers (GPT) - 4 years

Availability

Part-time

Preferred Environment

Linux

The most amazing...

...project I've developed is a machine learning system for determining types and physical properties of construction materials in BIM model.

Work Experience

Data Scientist

2019 - PRESENT
Altoros
  • Constructed a proof of concept (PoC) for field crop detection and segmentation, tracking crop health status, and detection of natural hazards.
  • Built a PoC for automating PDF processing functions with machine-learning algorithms that detected structural elements, extracted text, tables, graphs, and table of contents (ToC) from documents with a complex layout.
  • Developed microservices for drivers' behavior analysis, route map matching, and trip summary calculation.
  • Created a model for route and destination prediction based on the Hidden Markov Model.
Technologies: GIS, Kubernetes, Docker, Flask, FastAPI, Neo4j, Keras, TensorFlow, Python

Data Scientist

2017 - 2018
Kreo Software
  • Developed a set of tools for Amazon Mechanical Turk (MTurk): a framework for publishing tasks, validating work, and selecting and training workers.
  • Supervised several MTurk projects with challenging NLP tasks that required a rigorous screening of workers.
  • Improved the classifier of construction elements in the Uniclass system.
  • Optimized the classifier for production and deployed the trained model.
Technologies: Amazon Web Services (AWS), MongoDB, React, Amazon Mechanical Turk, Neo4j, SpaCy, Pandas, C#, JavaScript, Python

Data Scientist

2016 - 2017
Kinross Research
  • Developed an entity extraction model for extracting dimensions, squares, volumes, ranges, and so on with corresponding units from a textual description of construction elements. I built two versions of the model: a rule-based version and a version based on a recurrent neural network.
  • Created a data-specific PDF table extractor and integrated the extracted data into the knowledge base.
  • Built a web application: a type of annotation tool for labeling data for ML models and for the core project engine.
Technologies: JavaScript, Django, Pandas, TensorFlow, Python

ECG Analysis

While studying in the School of Data Science at Yandex, I participated in a Kaggle competition. The goal was to determine the presence of the disease according to the patient's ECG. Due to the nature of data, it was a great experience in feature engineering. I took fifth place out of 174.

Dotfiles

https://github.com/SnichOne/dotfiles
These are my dotfiles along with the installation script to set up a Linux machine.

Languages

Python, C++, C, SQL, C#, Java, JavaScript

Frameworks

Flask, Django

Libraries/APIs

TensorFlow, SpaCy, Keras, Scikit-learn, SciPy, Pandas, Matplotlib, React, PyTorch

Tools

Git, RabbitMQ, GIS

Paradigms

CRISP-DM, Agile, Concurrent Programming, Functional Programming, Test-driven Development (TDD), Continuous Delivery (CD), Data Science

Other

Algorithms, Amazon Mechanical Turk, Natural Language Processing (NLP), GPT, Generative Pre-trained Transformers (GPT), Machine Learning, Deep Learning, Neural Networks, Statistics, FastAPI, Computer Vision

Platforms

Linux, Docker, Kubernetes, Amazon Web Services (AWS)

Storage

PostgreSQL, Neo4j, NoSQL, MongoDB

2012 - 2017

Specialist's Degree (Equivalent to a Master's Degree) in Computer Security

Belarusian State University - Minsk, Belarus

SEPTEMBER 2019 - PRESENT

AI from the Data Center to the Edge—An Optimized Path Using Intel® Architecture

Intel Corporation

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