Logo
Bohdan – Deep Learning, Data Science, NLP, experts in Lemon.io

Bohdan

From Croatia (GMT+2)

flag
Data ScientistSenior
Hire developer
7 years of commercial experience
Adtech
Advertising
AI
Cybersecurity
Data analytics
Marketing
Sports
Telecommunications
B2B
B2C
Data monetization
Open source
Trade
AI software
Communication tools
CRM
NLP software
Lemon.io stats

Bohdan – Deep Learning, Data Science, NLP

Meet Bohdan, a Data Scientist with 7 years of expertise in the IT field. His extensive knowledge spans a broad spectrum of areas, including network anomaly detection, Natural Language Processing (NLP), time series analysis (with a specialization in stock and crypto market analysis), statistics, as well as applications in advertising and fintech through the implementation of machine learning techniques. Bohdan has a rich portfolio of successfully developed AI projects and is known for his proactive approach. If you're looking for a Data Scientist, Bohdan is the one you've been dreaming about.

Main technologies
Deep Learning
6 years
Data Science
6 years
NLP
4 years
Python
6 years
Additional skills
GCP
GPT
MongoDB
PyTorch
Scikit-learn
.NET
Microsoft SQL Server
Docker
Java
BigQuery
Apache Airflow
Machine learning
Microsoft Azure
AI
OpenCV
C++
Pandas
NumPy
Tensorflow
Matplotlib
Rewards and achievements
June 2024: Susanna Summary
Ready to start
ASAP
Direct hire
Potentially possible

Experience Highlights

Senior Data Scientist
Jun 2021 - Aug 20232 years 2 months
Project Overview

B2B ad tech project, mostly focused on real-time bidding models and NLP-based ad campaign ranking system with millions of daily queries and managing/monitoring available ad inventory.

Skeleton
Skeleton
Skeleton
Responsibilities:
  • Developed ad campaign/website ranking system using the latest NLP models for millions of websites and thousands of campaigns daily, optimized storage costs, and employed heuristics and algorithmic optimization
  • Developed model monitoring tools, dashboards, and back-testing instruments
  • Conducted A/B testing of RTB models and different features
  • Reduced bot traffic by 1.5%
  • Took part in GPT-3/4/J, Chat-GPT POC development
Project Tech stack:
PyTorch
GCP
GCP Compute Engine
BigQuery
Apache Airflow
NLP
Deep Learning
Machine leaning
NLP/AI Engineer
Dec 2018 - Jun 20212 years 5 months
Project Overview

Internal securities data provider with conversational AI capable of text2code generation (including complex aggregate requests), basic dialogue capabilities, embedding-based search engine, and a recommender system.

Skeleton
Skeleton
Skeleton
Responsibilities:
  • Developed hybrid approach search engines/content-based recommendation systems, measured model effectiveness, beating Elastic Search nDCG score by 70%
  • Developed conversational AI models capable of translating user utterances into SQL/NoSQL requests
  • Created synthetic datasets from scratch, used data augmentation techniques
  • Took part in speech recognition R&D
  • Fine-tuned BERT-based NLP models to specific domains
Project Tech stack:
Python
NLTK
MongoDB
NLP
Flask
Minor open source contributor
Oct 2018 - Oct 2018
Project Overview

Open source python clustering library.

Skeleton
Skeleton
Skeleton
Responsibilities:
  • Was in charge of a visualization task of genetic algorithm clustering during his own research
  • Used PyClustering as an open-source library, however during his experiments he noticed incorrect crossover mask generation and certain issues with constructor parameters
  • Fixed the bug with mask generation
  • Slightly refactored the constructor so it was able to have the required parameters passed correctly
  • The changes were introduced manually in PR #474
Project Tech stack:
Python
Data Science
Data Scientist
Jul 2017 - Dec 20175 months
Project Overview

An AI start-up is trying to monetize ML in every conceivable way. From predicting sports outcomes and tracking players from video feeds to reinforcement learning trading agents.

Skeleton
Skeleton
Skeleton
Responsibilities:
  • Created a sports outcome prediction model and paired it with a profitable bet allocation strategy
  • Took part in the development of tracking through detection model (background subtraction + Kalman filter) for football player analysis, optimized reading stream, improved FPS throughput from 30 to 45 fps
  • Developed several Q-learning-based trading agents, beating the annual return benchmark by 1.5%
Project Tech stack:
.NET
.NET Core
Python
Microsoft Azure
Microsoft SQL Server
MongoDB
AI
Machine learning
C++
OpenCV
Junior C# Developer/ML Developer
Aug 2015 - Jun 20171 year 9 months
Project Overview

IP telephony/B2C ads focused CRM with Google analytics/social media integration and basic conversion outcome predictive models.

Skeleton
Skeleton
Skeleton
Responsibilities:
  • Was responsible for REST API development
  • Was in charge of oAuth2.0 integration
  • Prototyped and integrated a regression model for conversion modeling using Accord.Net
  • Created clustering based on client website activity
  • Integrated speech-to-text translation of recorded phone calls into the CRM using Google Speech API
Project Tech stack:
.NET
.NET Core
AI
Data Science
Microsoft Azure
Machine learning
ASP.NET MVC

Education

2019
Computer Science / Artificial Intelligence
MSc

Copyright © 2024 lemon.io. All rights reserved.