Traffic Prediction Platform and Staff Scheduling Engine. With 25.000 employees and 2.500 branches Nova Poshta is the biggest private logistics company in Ukraine. The main offering is express delivery of parcels which is extremely important for internet shoppers. As salaries rise and competition is getting harder, staff allocation needs to be improved to prevent over-staffing on the one hand and queues on the other hand. Nova Poshta only started the journey of using machine learning, artificial intelligence etc. to optimize efficiency. Using machine learning we predict the number of parcels/customers for each branch and each hour of the day. The subsequent software component uses this information and creates a work schedule for each branch. It is a classic problem of artificial intelligence (constraint satisfaction problem) and we use the typical algorithms to solve them.I have built the first version of the software by myself and then used the results to convince top management that investing more in this direction is reasonable. After that I was allowed to hire a small team. Now we enhance the product as a team of 6 people and are in the middle of roll-out to production.
Tasks:
2017 - 2018: Engineering
Role: Machine Learning Engineer
Customer: GliaLab, Chicago
Tasks:
Prototype / Proof of Concept of core product for GliaLab?s goal was to create a SAAS platform that allows radiologists to upload a mammogram and obtain a second opinion regarding potentially maign tissue. I designed and developed the prototype as a web application using Python/Flask running on Nginx. In the backend the platform starts up on demand additional AWS/EC2 instances to run prediction jobs on powerful GPUs and shuts them down when idle. I also developed the entire pipeline of image preprocessing with OpenCV (for example normalize contrast, apply sliding window algorithms, histogram normalization) and machine learning algorithms in Python/Keras/Tensorflow running on AWS. I worked a lot with algorithms like AlexNet, VGG16, ResNet. The platform is a multi-threaded microservices architecture. Modern X-Ray devices create as an output a special file format called DICOM. The platform can read and write DICOM images. GliaLab planned to do an ICO and had very high profile supporters. But parrently they ran into regulatory issues relating to SEC regulations in the USA. Unfortunately the project was then put on hold.
2016-2018: Consulting
Role: COO
Customer: on request
Tasks:
This is an IT outsourcing/outstaffing/recruiting company with offices in Stuttgart, Kiev and Kairo. Beginning of 2016 the company was in a very critical situation. The CEO asked me if I could assist in turning this situation around. I had some free time as I just left Ciklum and focused on studying (see Udacity below). I then provided my knowledge in IT, finance, management and client relationship to Evolvice. There was a legal battle to win and liquidity was almost zero. To survive, the company had to win one specific client. That happened and the company is today doing ok and has 80 employees. In 2016 it had approx. 30 employees. I still help the company sometimes when they need ?technical sales?. One frequent activity was to hold technical interviews with potential new employees. I handled such technical interviews and over the time it accumulated to approx 250 interviews.
2013-2015: Designed and implementation
Role: on request
Customer: on request
Place of work: Kiev, Ukraine
Tasks:
This is one of the top 5 outsourcing companies in Eastern Europe and has approximately 3.000 employees. It offers outstaffing and project outsourcing and consulting services. My responsibility was to manage a turnaround of the project outsourcing business line with 150 employees. The business line was making losses and client satisfaction was low. Staff turnover was high. I managed the turnaround and doubled the size of the business line. It required the application of contemporary HR methodologies as well as financial controlling and restructuring of processes. In this context we also did an ISO 9001:2008 quality system certification.
2012-2013: Turnaround Management
Role: Partner
Customer: on request
Place of work: Kiev, Ukraine
Tasks:
This is a small accounting outsourcing and tax advisory firm in Kiev with clients from Germany. After finishing the MBA and MSc I wanted to do something different than programming and found there an opportunity to do so. When the economy in Ukraine deteriorated, which ultimately led to the revolution, many German clients shut down their operations in Ukraine and Otten Consulting significantly shrunk. This led to the decision of accepting an offer by Ciklum.
2008 - 2011: Development
Role: Java Developer
Customer: Unicredit Bank - Investment Banking Department
Place of work: Munich
Tasks:
The bank had several trading systems for all kinds of securities. The traders wanted to connect to furter stock exchanges in Poland, Czech Republic, Turkey and obtain high frequency trading data from the Futures trading platform Eurex in Frankfurt. My job was to connect the bank to these stock exchanges. In addition to that, the bank had self-developed tools to calculate funds that were also connected to the stock exchange. I was also involved in the further development of some of these tools.
1996-2008: data analysis, management and simulation (Excel, MS-Access)
Role: Developer/Analyst
Customer: The Boston Consulting Group and Bain & Company
Place of work: Munich
Tasks:
I worked for these companies as an external/freelancer in the IT sphere. The consultants involved me regularly on-site at the client. My role was to analyze data and to build specific tools that assist consultants in analysis and simulation. I also programmed for a different department where we created an internal web-based platform for handling the very complex HR processes of BCG. In particular, gathering, processing and visualizing text-based and numerical data. Other components included the handling of hiring events and maintaining relationships with good candidates For example:
BrainExtension - Machine Learning powered Language learning tool
Tasks:
This is my own ?side project?. I love learning foreign languages and this tool helps me to maintain and expand my vocabulary. It measures and predicts the learning and forgetting pattern for each user. By using this information it optimizes the learning efficiency. It also leverages the translation API of (URL on request). I am actively working on this project and will soon start digital marketing in order to make it available for the public. A the code can be seen here: URL on request
Self Driving Car Engineering Program
Customer: Udacity
Tasks:
In order to upgrade my skills I applied for this program and got accepted. It is a tough 9 months program that teaches most of the IT aspects of self driving cars. This mainly includes computer vision, sensor fusion (radar + video + laser), machine learning, decision making, localization, robotics (using ROS - robot operating system) as well as steering of the car taking into account the laws of physics (mass inertia, gravity, friction). Some of the projects I did can be seen on GitHub:
Data Science Specialization in R language
Customer: Coursera
Tasks:
To upgrade my skills I did this 10 months program. It consists of 9 courses in data science plus one capstone project. The capstone project was realized as a shinyapps.io application. uses 8.2 mio n-Grams generated from Twitter tweets and predicts via statistics the next word. The application is live: (URL on request)
2017
Artificial Intelligence Nanodegree Program
Udacity (URL on request)
2016 - 2017
Self Driving Car Nanodegree Program
Udacity
2016
Various courses on Coursera in Big data (Hadoop, Spark, Hive, Knime,...).
2015 - 2016
Specialization in Data Science
John Hopkins University/Coursera (10 months). See (URL on request)
2008 - 2011
MBA and MSc in Finance and Management
Open University in UK (URL on request)
Skills:
IT-Management:
Agile, Lean, Scrum, Waterfall, HR management specific to the IT sphere
General management:
Financial analysis and planning, structuring of production processes, turnaround management, operational improvement, ISO 9001:2008 certification, building corporate culture, bonus and incentive schemes
Dashboard/Analytics:
Microsoft Power BI
Dash/Plotly
ETL/Streaming/Analysis:
Apache Airflow, Spark, Kafka, TIBCO
Machine Learning:
TensorFlow, Keras, Scikit
Computer Vision:
OpenCV, scikit-image
Robotics:
ROS
Medical and financial protocols:
DICOM, OpenFast, FastFix
Cloud:
AWS EC2 / S3, Google Cloud Compute Engine and BigQuery
Traffic Prediction Platform and Staff Scheduling Engine. With 25.000 employees and 2.500 branches Nova Poshta is the biggest private logistics company in Ukraine. The main offering is express delivery of parcels which is extremely important for internet shoppers. As salaries rise and competition is getting harder, staff allocation needs to be improved to prevent over-staffing on the one hand and queues on the other hand. Nova Poshta only started the journey of using machine learning, artificial intelligence etc. to optimize efficiency. Using machine learning we predict the number of parcels/customers for each branch and each hour of the day. The subsequent software component uses this information and creates a work schedule for each branch. It is a classic problem of artificial intelligence (constraint satisfaction problem) and we use the typical algorithms to solve them.I have built the first version of the software by myself and then used the results to convince top management that investing more in this direction is reasonable. After that I was allowed to hire a small team. Now we enhance the product as a team of 6 people and are in the middle of roll-out to production.
Tasks:
2017 - 2018: Engineering
Role: Machine Learning Engineer
Customer: GliaLab, Chicago
Tasks:
Prototype / Proof of Concept of core product for GliaLab?s goal was to create a SAAS platform that allows radiologists to upload a mammogram and obtain a second opinion regarding potentially maign tissue. I designed and developed the prototype as a web application using Python/Flask running on Nginx. In the backend the platform starts up on demand additional AWS/EC2 instances to run prediction jobs on powerful GPUs and shuts them down when idle. I also developed the entire pipeline of image preprocessing with OpenCV (for example normalize contrast, apply sliding window algorithms, histogram normalization) and machine learning algorithms in Python/Keras/Tensorflow running on AWS. I worked a lot with algorithms like AlexNet, VGG16, ResNet. The platform is a multi-threaded microservices architecture. Modern X-Ray devices create as an output a special file format called DICOM. The platform can read and write DICOM images. GliaLab planned to do an ICO and had very high profile supporters. But parrently they ran into regulatory issues relating to SEC regulations in the USA. Unfortunately the project was then put on hold.
2016-2018: Consulting
Role: COO
Customer: on request
Tasks:
This is an IT outsourcing/outstaffing/recruiting company with offices in Stuttgart, Kiev and Kairo. Beginning of 2016 the company was in a very critical situation. The CEO asked me if I could assist in turning this situation around. I had some free time as I just left Ciklum and focused on studying (see Udacity below). I then provided my knowledge in IT, finance, management and client relationship to Evolvice. There was a legal battle to win and liquidity was almost zero. To survive, the company had to win one specific client. That happened and the company is today doing ok and has 80 employees. In 2016 it had approx. 30 employees. I still help the company sometimes when they need ?technical sales?. One frequent activity was to hold technical interviews with potential new employees. I handled such technical interviews and over the time it accumulated to approx 250 interviews.
2013-2015: Designed and implementation
Role: on request
Customer: on request
Place of work: Kiev, Ukraine
Tasks:
This is one of the top 5 outsourcing companies in Eastern Europe and has approximately 3.000 employees. It offers outstaffing and project outsourcing and consulting services. My responsibility was to manage a turnaround of the project outsourcing business line with 150 employees. The business line was making losses and client satisfaction was low. Staff turnover was high. I managed the turnaround and doubled the size of the business line. It required the application of contemporary HR methodologies as well as financial controlling and restructuring of processes. In this context we also did an ISO 9001:2008 quality system certification.
2012-2013: Turnaround Management
Role: Partner
Customer: on request
Place of work: Kiev, Ukraine
Tasks:
This is a small accounting outsourcing and tax advisory firm in Kiev with clients from Germany. After finishing the MBA and MSc I wanted to do something different than programming and found there an opportunity to do so. When the economy in Ukraine deteriorated, which ultimately led to the revolution, many German clients shut down their operations in Ukraine and Otten Consulting significantly shrunk. This led to the decision of accepting an offer by Ciklum.
2008 - 2011: Development
Role: Java Developer
Customer: Unicredit Bank - Investment Banking Department
Place of work: Munich
Tasks:
The bank had several trading systems for all kinds of securities. The traders wanted to connect to furter stock exchanges in Poland, Czech Republic, Turkey and obtain high frequency trading data from the Futures trading platform Eurex in Frankfurt. My job was to connect the bank to these stock exchanges. In addition to that, the bank had self-developed tools to calculate funds that were also connected to the stock exchange. I was also involved in the further development of some of these tools.
1996-2008: data analysis, management and simulation (Excel, MS-Access)
Role: Developer/Analyst
Customer: The Boston Consulting Group and Bain & Company
Place of work: Munich
Tasks:
I worked for these companies as an external/freelancer in the IT sphere. The consultants involved me regularly on-site at the client. My role was to analyze data and to build specific tools that assist consultants in analysis and simulation. I also programmed for a different department where we created an internal web-based platform for handling the very complex HR processes of BCG. In particular, gathering, processing and visualizing text-based and numerical data. Other components included the handling of hiring events and maintaining relationships with good candidates For example:
BrainExtension - Machine Learning powered Language learning tool
Tasks:
This is my own ?side project?. I love learning foreign languages and this tool helps me to maintain and expand my vocabulary. It measures and predicts the learning and forgetting pattern for each user. By using this information it optimizes the learning efficiency. It also leverages the translation API of (URL on request). I am actively working on this project and will soon start digital marketing in order to make it available for the public. A the code can be seen here: URL on request
Self Driving Car Engineering Program
Customer: Udacity
Tasks:
In order to upgrade my skills I applied for this program and got accepted. It is a tough 9 months program that teaches most of the IT aspects of self driving cars. This mainly includes computer vision, sensor fusion (radar + video + laser), machine learning, decision making, localization, robotics (using ROS - robot operating system) as well as steering of the car taking into account the laws of physics (mass inertia, gravity, friction). Some of the projects I did can be seen on GitHub:
Data Science Specialization in R language
Customer: Coursera
Tasks:
To upgrade my skills I did this 10 months program. It consists of 9 courses in data science plus one capstone project. The capstone project was realized as a shinyapps.io application. uses 8.2 mio n-Grams generated from Twitter tweets and predicts via statistics the next word. The application is live: (URL on request)
2017
Artificial Intelligence Nanodegree Program
Udacity (URL on request)
2016 - 2017
Self Driving Car Nanodegree Program
Udacity
2016
Various courses on Coursera in Big data (Hadoop, Spark, Hive, Knime,...).
2015 - 2016
Specialization in Data Science
John Hopkins University/Coursera (10 months). See (URL on request)
2008 - 2011
MBA and MSc in Finance and Management
Open University in UK (URL on request)
Skills:
IT-Management:
Agile, Lean, Scrum, Waterfall, HR management specific to the IT sphere
General management:
Financial analysis and planning, structuring of production processes, turnaround management, operational improvement, ISO 9001:2008 certification, building corporate culture, bonus and incentive schemes
Dashboard/Analytics:
Microsoft Power BI
Dash/Plotly
ETL/Streaming/Analysis:
Apache Airflow, Spark, Kafka, TIBCO
Machine Learning:
TensorFlow, Keras, Scikit
Computer Vision:
OpenCV, scikit-image
Robotics:
ROS
Medical and financial protocols:
DICOM, OpenFast, FastFix
Cloud:
AWS EC2 / S3, Google Cloud Compute Engine and BigQuery