Dmitry is available for hire

Dmitry Savostyanov

Verified Expert in Engineering

Machine Learning Engineer and Developer

Vilnius, Lithuania

Toptal member since July 1, 2022

Expertise

Machine Learning Data Visualization SQL Python WordPress Development Git Cloud Engineering Django Google Kubernetes Engine (GKE)Algorithms NLP SAS

Bio

Dmitry is a machine learning engineer with five years of experience in the game development industry, eCommerce, and fintech. He is passionate about technologies and demonstrates strong leadership and organizational skills. Dmitry communicates well with both business and engineers.

Portfolio

Gosu

Python 3, Machine Learning, Google Cloud Platform (GCP), Leadership...

SAS

SAS, SAS Enterprise Miner, SAS Enterprise Guide, R, Python 3, Data Science, SQL...

Experience

Python 3 - 5 years
Pandas - 5 years
Machine Learning - 5 years
Git - 5 years
Matplotlib - 5 years
Google Cloud Platform (GCP) - 3 years
WordPress - 1 year

Availability

Part-time

Preferred Environment

Slack, GitHub, Notion, Python 3, Google Cloud Platform (GCP), Pandas, PostgreSQL, CatBoost, PyTorch, Docker

The most amazing...

...thing I've launched is a voice assistant for gamers with a million monthly active users, resulting in the startup being acquired by a game publishing company.

Work Experience

Head of Machine Learning

2017 - 2022

Gosu

Led a team of 15 members, including machine learning (ML) engineers, software engineers, UI/UX designers, product managers, and product analysts.
Launched a new product – a voice assistant for gamers. It increased the company's revenue ten times. At its peak, the product audience reached one million monthly active users, resulting in the startup being acquired by a game publishing company.
Designed and implemented analytical infrastructure as a service for external game development studios, which allowed storing the data from different games and simplified the ML models' transferring process.
Used a churn prediction model to send push notifications between gaming sessions and increase the retention rate.
Created a recommender system to provide personalized in-game offers to increase game metrics, such as a conversion rate and LTV.
Trained a question-answering model for games. It uses a combination of BERT and TF-IDF to find the correct and short answers to gamers' questions in thousands of documents.
Oversaw the development, deployment, and support of the auto post-match analysis for Dota 2 and PUBG. Processed 100,000 GB of raw gaming data in two years.
Developed, deployed, and supported algorithms for automatic video-highlight detection in games, allowing gamers to create more than 10,000 videos.

Technologies: Python 3, Machine Learning, Google Cloud Platform (GCP), Leadership, Business Strategy, Product Management, IT Project Management, Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), Django, PostgreSQL, Google BigQuery, Pandas, Matplotlib, Scikit-learn, CatBoost, PyTorch, Redis, Apache Kafka, Redash, Grafana, Git, GitHub, Docker, Google Kubernetes Engine (GKE), Dialogflow, Data Science, SQL, Python, Data Visualization

Junior Data Scientist

2016 - 2017

SAS

Created a fraud detection model based on transaction data, resulting in the sales team closing a deal on the integration of SAS software.
Collected additional data for the bank's customer churn prediction model, which combined with feature engineering to increase ROC AUC from 0.65 to around 0.73.
Analyzed marketing campaign data and calculated conversion rates over different cohorts and segments of users.

Technologies: SAS, SAS Enterprise Miner, SAS Enterprise Guide, R, Python 3, Data Science, SQL, Python, Data Visualization

Experience

Voice Assistant for Gamers

I oversaw the whole business unit working on this desktop and web app for gamers. It uses ML to provide advice in real time and answer gamers' questions. Also, it offers a detailed post-match analysis with statistics and recommendations regarding matches in Dota 2, League of Legends, and PUBG. Finally, it allows users to automatically create video highlights after the game session.

Before this, I was an ML engineer on the same project. Our team was focused on the post-match analysis, video highlights, back-end features, and providing APIs for front-end engineers.

Despize Boosting

This is my eCommerce pet project focused on items and services for gamers. Users could order coaching sessions, items, and gold in World of Warcraft, Call of Duty, and other games.

I created and maintained the website using WordPress and WooCommerce. It allowed me to save resources and hire marketing, content, and design specialists.

Education

2013 - 2017

Bachelor's Degree in Computer Science

National Research University Higher School of Economics - Moscow, Russia

Skills

Libraries/APIs

Pandas, Scikit-learn, Matplotlib, CatBoost, PyTorch, XGBoost, jQuery

Tools

Slack, GitHub, Notion, Redash, Grafana, Git, Google Kubernetes Engine (GKE), SAS Enterprise Miner, SAS Enterprise Guide, Dialogflow, LiteSpeed Web Server (LSWS), Apache HTTP Server

Languages

SQL, Python, Python 3, SAS, R, PHP, JavaScript

Platforms

WordPress, Google Cloud Platform (GCP), Docker, Apache Kafka, WooCommerce

Frameworks

Django, LightGBM, Flask

Storage

PostgreSQL, Redis

Other

Machine Learning, Data Science, Data Visualization, Applied Mathematics, Software Engineering, Creative Problem Solving, Algorithms, Leadership, Business Strategy, Product Management, IT Project Management, Natural Language Processing (NLP), Google BigQuery, 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.

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