Vasil Yordanov, Developer in Varna, Bulgaria
Vasil is available for hire
Hire Vasil

Vasil Yordanov

Verified Expert  in Engineering

Machine Learning Engineer and Developer

Location
Varna, Bulgaria
Toptal Member Since
October 25, 2022

Vasil is a skilled machine learning engineer and cloud architect with 10 years of experience in signal processing, computer vision, object detection, and time-series and tabular data. He is fluent in Python, TensorFlow, Docker, and Kubernetes and has designed end-to-end ML systems on Google Cloud and Microsoft Azure. Vasil is also certified as a machine learning and data engineer and TensorFlow Developer.

Portfolio

SoftServe
Google Cloud Platform (GCP), Azure, TensorFlow, Vertex AI...
SoftServe
TensorFlow, Vertex AI, PyTorch, Python 3, Jupyter Notebook...
Ocado Group
Python 3, Google BigQuery, Google Kubernetes Engine (GKE), Vertex AI...

Experience

Availability

Part-time

Preferred Environment

Windows 11, Ubuntu, IntelliJ IDEA, PyCharm, Google Cloud Platform (GCP), Jupyter Notebook, Python 3

The most amazing...

...thing I've worked on is an IoT and ML system for monitoring health data from a fleet of smart devices worn by elderly patients.

Work Experience

Machine Learning Architect

2022 - PRESENT
SoftServe
  • Designed enterprise MLOps solutions on GCP and Azure.
  • Oversaw and managed the development teams through the implementation of various solutions.
  • Designed and took part in the implementation of an NLP analytics system on GCP.
  • Designed and implemented enterprise LLM-powered applications for Semantic Search, document questions and answers, as well as OpenAPI REST Agent.
Technologies: Google Cloud Platform (GCP), Azure, TensorFlow, Vertex AI, Machine Learning Operations (MLOps), Python 3, Machine Learning, Python, Artificial Intelligence (AI), Microservices Architecture, Docker, Azure DevOps, PostgreSQL, Pandas, Data Engineering, Dataiku, Seldon, Kubeflow, IntelliJ IDEA, OpenAI GPT-3 API, Artificial General Intelligence (AGI), Flask, Large Language Models (LLMs)

Senior Machine Learning Engineer

2021 - 2022
SoftServe
  • Developed pipelines based on Kubeflow and Vertex for continuous training (CT) of machine learning models.
  • Implemented distributed training of TensorFlow models on GKE, Vertex AI, and on-premise hardware.
  • Developed cloud dataflow for batch ETL pipelines using Apache Beam.
Technologies: TensorFlow, Vertex AI, PyTorch, Python 3, Jupyter Notebook, Convolutional Neural Networks (CNN), Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), Computer Science, Google Cloud Platform (GCP), Machine Learning Operations (MLOps), Object Detection, Machine Learning, Python, Artificial Intelligence (AI), Microservices Architecture, Docker, Azure DevOps, PostgreSQL, Pandas, Data Engineering, Predictive Modeling, Kubeflow, IntelliJ IDEA, SQL, Image Processing, Flask

Machine Learning Engineer

2020 - 2021
Ocado Group
  • Enabled predictive maintenance of warehouse delivery robots by building machine learning models.
  • Developed machine learning models for predictive maintenance of warehouse railway system.
  • Used Python and Google BigQuery to develop ETL pipelines.
Technologies: Python 3, Google BigQuery, Google Kubernetes Engine (GKE), Vertex AI, Google Cloud Storage, Jupyter Notebook, Data Science, Recurrent Neural Networks (RNNs), Computer Vision, Computer Science, Google Cloud Platform (GCP), TensorFlow, Object Detection, Machine Learning, Python, Artificial Intelligence (AI), Microservices Architecture, Docker, PostgreSQL, Pandas, Data Engineering, Predictive Modeling, IntelliJ IDEA, SQL, Image Processing

Machine Learning Engineer

2019 - 2020
Medical Monitoring Center
  • Designed and built streaming data and ML pipelines in Kafka Streams and Python.
  • Enabled pattern recognition in time-series IoT data by designing and training convolutional (CNN) and recurrent (RNN) neural networks.
  • Developed, containerized, and deployed Python and Java in GKE.
Technologies: Python 3, TensorFlow, Apache Kafka, Jupyter Notebook, Google Kubernetes Engine (GKE), Java, Google Pub/Sub, Redis, Google Cloud Storage, Data Science, Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNNs), Computer Vision, Computer Science, Google Cloud Platform (GCP), Machine Learning, Python, Artificial Intelligence (AI), Microservices Architecture, Docker, PostgreSQL, Pandas, Data Engineering, Predictive Modeling, IntelliJ IDEA, SQL, Image Processing

LLM-powered OpenAPI Agent

The project I was involved in focused on developing an LLM application designed to provide a chatbot interface for REST APIs. As the machine learning architect and developer, I played a crucial role in its implementation. I utilized various tools and frameworks to enhance the application's functionality, including Chainlit, LangChain, PaLM, and ChatGPT.

LLM-powered Enterprise Document Q&A Application

The project I was involved in focused on developing an enterprise document Q&A application powered by LLM technology. As the machine learning architect and developer, I played a crucial role in its implementation. We utilized various tools and frameworks to enhance the application's functionality, including Streamlit, LangChain, PaLM, ChatGPT, and Hugging Face.

Our application aimed to address the challenge of efficiently extracting information from vast amounts of textual data within an enterprise setting. By leveraging LLM technology, we were able to develop a robust question-and-answer system capable of understanding and responding to queries based on the contents of documents.

Enterprise MLOps Architecture for Microsoft Azure

The project, which aimed to develop an enterprise machine learning operations (MLOps) architecture for a UK-based, multinational technology company, had a duration of three months. As the machine learning architect, I led a team of machine learning and DevOps engineers in the development of the solution. The architecture heavily relied on 3rd-party tools, including Dataiku and Seldon, enabling seamless collaboration and an end-to-end MLOps lifecycle. The developed solution was deployed on Microsoft Azure, allowing for efficient management of the entire MLOps lifecycle, including data management, model training, and deployment.

Social Sentiment Analysis System

The social sentiment analysis system was a remarkable project that I had the pleasure of leading as a machine learning architect. Our development team of ML, MLOps, and front-end engineers built a sophisticated solution based on a BERT model implemented in TensorFlow. The system tracks user sentiment on specified topics in near real time and utilizes only server-less components in Google Cloud. The technology stack includes Vertex Pipelines, Cloud Function, Cloud Run, BigQuery, and Cloud Storage.

The project was completed in three months, and it also included the implementation of a management API in Flask.

Enterprise MLOps Architecture for Google Cloud

During this six-month project, our team designed and implemented various landing zones for development, staging, monitoring, and production. As the machine learning architect, I led the development team comprising machine learning and DevOps engineers to develop an enterprise machine learning operations architecture for an Asian-based multinational technology company. Our solution integrated various cloud-native and third-party systems such as Vertex AI, BigQuery, and Cloud Build to enable seamless collaboration and an end-to-end MLOps lifecycle. We also integrated popular machine learning frameworks such as TensorFlow and PyTorch for model training and deployment. Our architecture enabled efficient model management and reproducibility across all stages of development.

Serverless Python Packages Orchestration System (GCP)

In this project, I worked on a serverless system designed to orchestrate Python-source distributions and Jupyter Notebooks on the Google Cloud Platform. Key features include scheduling Python packages and notebooks as cron jobs, ad-hoc execution of Python packages and notebooks, developing a Python API for Python package and notebook management, and integrating with third-party APIs. As a machine cloud architect, I led the development team consisting of machine learning and back-end engineers during the project implementation.

Warehouse Object Detection System

For 6 months, I worked as a machine learning engineer in a team that developed an object detection model using TensorFlow. The model aimed to identify and detect robots on CCTV camera streams, and I was responsible for the error analysis of different models, the design of datasets to enhance model performance, and the setting up of a cloud architecture for distributed training.

Healthcare IoT Platform

As a data and machine learning engineer in a European startup, I worked on a cloud machine learning system for ingesting, processing, and inferring bio-metric and motion data in near real time. Key features included inference of streaming data, batch processing, and cryptographic key management. The system utilized Kafka and Kafka Streams for data ingestion and processing, PostgreSQL for data storage, and APIs for integrating the system with external services. My responsibilities also included training deep learning models in TensorFlow and implementing data and inference pipelines for production deployment.
2007 - 2012

Master's Degree in Naval Architecture

Technical University of Varna - Varna, Bulgaria

MARCH 2023 - PRESENT

Generative Adversarial Networks (GANs) Specialization

Coursera

JANUARY 2023 - PRESENT

Advanced Computer Vision with TensorFlow

Coursera

JANUARY 2022 - JANUARY 2025

TensorFlow Developer

TensorFlow

OCTOBER 2021 - PRESENT

TensorFlow Developer Specialization

Coursera

SEPTEMBER 2021 - PRESENT

Machine Learning Engineering for Production (MLOps)

Coursera

AUGUST 2021 - AUGUST 2023

Professional Machine Learning Engineer

Google Cloud

JULY 2021 - JULY 2023

Professional Data Engineer

Google Cloud

FEBRUARY 2019 - PRESENT

Deep Learning Specialization

Coursera

MAY 2018 - PRESENT

Machine Learning with TensorFlow on Google Cloud Platform Specialization

Coursera

MAY 2014 - PRESENT

Introduction to Computational Thinking and Data Science

edX

JANUARY 2014 - PRESENT

Introduction to Computer Science and Programming Using Python

edX

Libraries/APIs

TensorFlow, Pandas, PyTorch, OpenAPI

Tools

IntelliJ IDEA, PyCharm, Rhinoceros 3D, AutoCAD, Google Kubernetes Engine (GKE), Cloud Dataflow, Google Cloud Dataproc, Google Cloud Composer, Grafana, GitLab CI/CD, Azure Machine Learning, BigQuery

Languages

Python 3, Python, SQL, Excel VBA, Java, Scala

Paradigms

Data Science, Microservices Architecture, Azure DevOps, Linear Programming

Platforms

Vertex AI, Kubeflow, Jupyter Notebook, Google Cloud Platform (GCP), Ubuntu, Docker, Apache Kafka, Dataiku, Seldon, Azure, Google App Engine

Storage

Google Cloud Storage, PostgreSQL, Redis, Google Bigtable, Google Cloud Spanner, Google Cloud SQL, Google Cloud

Frameworks

Flask, Spark, Streamlit

Other

Google Pub/Sub, Google BigQuery, Convolutional Neural Networks (CNN), Machine Learning Operations (MLOps), Machine Learning, Object Detection, Artificial Intelligence (AI), Data Engineering, Google Cloud Build, Monte Carlo Simulations, Recurrent Neural Networks (RNNs), Natural Language Processing (NLP), Computer Vision, Computer Science, Time Series Analysis, Predictive Modeling, Image Processing, Generative Pre-trained Transformers (GPT), LangChain, OpenAI GPT-3 API, Artificial General Intelligence (AGI), Large Language Models (LLMs), TFX, Windows 11, Hydrodynamics, Statistical Methods, Statistical Learning, Pub/Sub, MLflow, Azure Databricks, Generative Adversarial Networks (GANs), Vertex Pipelines, CI/CD Pipelines

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