Logo
Anton – Python, Machine learning, Keras, experts in Lemon.io

Anton

From Ukraine (GMT+3)

flag
Machine Learning EngineerSenior
Hire developer
8 years of commercial experience
AI
Food and beverages
Machine learning
AI software
Lemon.io stats
2
projects done
168
hours worked
Open
to new offers

Anton – Python, Machine learning, Keras

Anton is a seasoned Machine Learning Engineer with 7 years of experience, specializing in computer vision, mono-depth estimation, and deep learning. With a software development background, he is adept at improving the design architecture of ML-based products. Anton has worked with clients like Samsung, showcasing his expertise and versatility in the field.

Main technologies
Python
6 years
Machine learning
6 years
Keras
5 years
NumPy
6 years
scikit-learn
5 years
Additional skills
C++
Git
Flask
Pandas
Git
Matplotlib
PyTorch
Web scraping
Ready to start
ASAP
Direct hire
Potentially possible

Experience Highlights

Deep learning research engineer
Sep 2023 - Dec 20233 months
Project Overview

In this project, a neural networks were trained to classify the type of car breakdown by sound. This algorithm is needed to replace diagnostics made by people with machine learning. Various models and approaches to data preprocessing were tested.

Skeleton
Skeleton
Skeleton
Responsibilities:
  • data preparation;
  • training neural networks;
  • metrics selection;
  • models evaluation;
  • model deployment;
Project Tech stack:
PyTorch
Python
Deep Learning
Deep Learning Research Engineer
Mar 2022 - Sep 20226 months
Project Overview

Participated in writing a custom framework for deep learning based on PyTorch Lightning and Hydra.

Skeleton
Skeleton
Skeleton
Responsibilities:
  • Added new NN architectures training pipelines;
  • implemented a new functionality.
Project Tech stack:
PyTorch
Python
Git
Neural Networks
Deep learning engineer
Jan 2021 - Apr 20221 year 2 months
Project Overview

This project was completely made by Anton from scratch. More than 5 million sports cards, along with metadata, were scraped from the Internet. After this, an artificial dataset was generated for training the card detector. The YOLO detector was trained, and embedding vectors were generated for each card. The final program had 2 parts (API and UI), which could detect cards in photos and find the most similar ones in the database.

Skeleton
Skeleton
Skeleton
Responsibilities:
  • web scraping;
  • artificial dataset generation;
  • neural networks training for object detection;
  • models evaluation;
  • embeddings vector generating;
  • API deployment;
  • creating a graphical interface.
Project Tech stack:
Python
Flask
Docker
Neural Networks
PyTorch
Machine Learning Engineer
Dec 2019 - Jan 20201 month
Project Overview

Training of an ML model for the prediction of food item cuisine based on the name, description, and price of restaurant menu items. It was made for HoReCa in the USA. Having a lot of menus from different restaurants (by web scraping), Anton analyzed what type of food is in trend with this model.

Skeleton
Skeleton
Skeleton
Responsibilities:
  • data preparation;
  • metrics selection;
  • models training;
  • models evaluation;
  • API deployment.
Project Tech stack:
Python
scikit-learn
NumPy
Pandas
Matplotlib
Flask
Git
Deep Learning Research Engineer
Nov 2017 - Feb 20183 months
Project Overview

Monodepth estimation model. This was done for a project in Samsung, which is under the NDA. An approach called "Deeper Depth Prediction with Fully Convolutional Residual Networks" (https://arxiv.org/abs/1606.00373) was used here.

Skeleton
Skeleton
Skeleton
Responsibilities:
  • data preparation;
  • models performance evaluation;
  • metrics selection;
  • neural networks training on GPUs.
Project Tech stack:
Python
Keras
CUDA
NumPy
Pandas
Matplotlib
Git
Deep Learning Research Engineer
Apr 2017 - Aug 20174 months
Project Overview

Object detector that will work quickly for the video. It was done for a project in Samsung, which is under the NDA. An approach called "Deep Feature Flow for Video Recognition" (https://arxiv.org/abs/1611.07715) was used here.

Skeleton
Skeleton
Skeleton
Responsibilities:
  • An investigation of different deep learning approaches;
  • data preparation;
  • models performance evaluation;
  • neural networks training on GPUs.
Project Tech stack:
Python
Keras
CUDA
NumPy
Pandas
Matplotlib
Git

Education

2018
Mathematics
Bachelor's

Copyright © 2024 lemon.io. All rights reserved.