Yuri Chemolosov, Solutions Architect and Developer in Montreal, QC, Canada
Yuri Chemolosov

Solutions Architect and Developer in Montreal, QC, Canada

Member since June 22, 2021
Yuri is a senior solutions architect with 20 years of experience across media and marketing (Shutterstock), automotive and manufacturing (Ford), telco (Verizon), and finance and security. With expertise in embedded, desktop, and cloud platforms, many complex production systems around the world carry his design or code. Yuri builds and leads high-performing, cross-domain teams; speaks a dozen computer languages and five human languages; and has a master's degree in computer engineering.
Yuri is now available for hire

Portfolio

  • Cerence Inc.
    Voice, Natural Language Understanding (NLU), Automotive, Azure...
  • Shutterstock
    AWS, Kubernetes, Fusion, Solr, Cassandra, Spark, TensorFlow, Java, Python...
  • Radialpoint by AppDirect
    Zuora, Zendesk, Salesforce, Microsoft Power BI, IBM Watson...

Experience

Location

Montreal, QC, Canada

Availability

Part-time

Preferred Environment

AWS, Kubernetes, Machine Learning, Serverless, Web Architecture, Startups, eCommerce, APIs, Azure, POC

The most amazing...

...project I've built was a POC for the question-answering AI system that beat Alexa and Siri.

Employment

  • Principal Solutions Architect

    2019 - PRESENT
    Cerence Inc.
    • Designed and led the integration of an intelligent digital assistant for Ford's Mustang Mach-E and F150. It integrates voice and Facebook chat clients with Ford's Sync4 embedded cloud hybrid system.
    • Restored and rebuilt two abandoned projects, recovering $100,000+ in professional services bills within the first two months of an engagement.
    • Created numerous POC projects for the CTO innovation squad, two of which were further grown into products: Cerence Extend, a touchless smartphone control using voice, and Cerence Browse, an AI-powered generic question-answering system.
    • Designed and led the development of an Azure-based serverless automotive digital twin platform, delivering a sub-200 ms overall latency car-to-cloud-to-mobile app for one million cars, with IoT traffic peaking at 200,000 TPS.
    Technologies: Voice, Natural Language Understanding (NLU), Automotive, Azure, Machine Learning, Node.js, Python, Serverless, Artificial Intelligence (AI), Proof of Concept (POC), Integration, POC, Confluence, Networking, API Integration, MVP Design, Data Science, APIs, Behavior-driven Development (BDD), Linux, Solution Design, Cloud, Distributed Systems, IT Strategy, Big Data Architecture, Architecture, Startups, Deep Learning, System Architecture, API Architecture, Data Strategy, SaaS, Technical Leadership, Third-party Integration, Docker, Microservices, JavaScript, SQL, HTML, CSS, Web Development, Leadership, Software Architecture, System Architecture Design, Microservices Architecture, Solution Architecture, Git, Azure IoT Hub, Jupyter, Azure Functions, Redis, REST, Protobuf, Data Engineering, NoSQL, React
  • Staff Software Engineer

    2015 - 2019
    Shutterstock
    • Led R&D initiatives that advanced the Shutterstock technology stack and algorithms to the next level: soundtrack instrument detection and behavioral and collaborative filtering for search and discovery.
    • Designed and led a no-downtime production migration to a new Cassandra-based media database hosting 2 billion+ photo, video, and music assets in multiple geolocations and reaching 120,000 TPS.
    • Led an initiative to redesign and implement a Fusion and Solr-based next-generation search system featuring AI/ML capabilities: an intention detection and image recommendation system handling 100 million+ daily interactions.
    Technologies: AWS, Kubernetes, Fusion, Solr, Cassandra, Spark, TensorFlow, Java, Python, Node.js, Artificial Intelligence (AI), Machine Learning, Algorithms, Apache Spark, Data Science, Confluence, Lucidchart, Spark ML, Networking, Serverless, API Integration, AWS Batch, Hadoop, Databricks, Integration, Proof of Concept (POC), MVP Design, APIs, Behavior-driven Development (BDD), Linux, Solution Design, Cloud, Distributed Systems, DataStax, IT Strategy, Big Data Architecture, eCommerce, Architecture, Startups, Audio Processing, Deep Learning, System Architecture, API Architecture, Data Strategy, SaaS, Technical Leadership, Third-party Integration, Docker, Microservices, JavaScript, SQL, Computer Vision, Web Development, Leadership, Software Architecture, System Architecture Design, Amazon Web Services (AWS), Microservices Architecture, Information Retrieval, Search, Elasticsearch, Solution Architecture, Git, AWS Lambda, Jupyter, Redis, REST, Amazon EC2, Data Engineering, NoSQL
  • Solutions Architect

    2009 - 2015
    Radialpoint by AppDirect
    • Led solutions design, implementation, and maintenance for major NA Telecom clients.
    • Delivered solutions for Verizon, Bell, Rogers, and Windstream.
    • Designed and partially developed a new Office 365 onboarding infrastructure for Videotron SMB clients.
    Technologies: Zuora, Zendesk, Salesforce, Microsoft Power BI, IBM Watson, Google Search Appliance, Web Architecture, Confluence, Lucidchart, Python, Networking, Machine Learning, API Integration, Knowledge Management, Integration, Data Science, APIs, Behavior-driven Development (BDD), Linux, Apache, Solution Design, Cloud, eCommerce, Architecture, System Architecture, API Architecture, Data Strategy, SaaS, Technical Leadership, Third-party Integration, Microservices, JavaScript, SQL, HTML, CSS, Web Development, Leadership, Software Architecture, System Architecture Design, Amazon Web Services (AWS), Microservices Architecture, Solution Architecture, Git, REST, Data Engineering
  • Web Architect

    2007 - 2009
    Aeroplan
    • Supervised outsourced teams of web and back-end developers.
    • Introduced the company to AWS cloud and established and promoted pipelines in the QA environments.
    • Redesigned and implemented a new development process that allowed parallel development and promotion of features for a monolith back-end system.
    Technologies: Java, Web, Mainframe, AWS, Networking, API Integration, Integration, Web Architecture, APIs, Oracle, Apache, Cloud, eCommerce, Architecture, System Architecture, API Architecture, Data Strategy, Technical Leadership, Third-party Integration, SQL, HTML, CSS, Web Development, Leadership, Software Architecture, System Architecture Design, Solution Architecture, REST
  • Senior Java Enterprise Developer

    2001 - 2007
    IG, Hoplo
    • Redesigned and led the implementation of a customer website authentication system for a $100 billion+ mutual fund company.
    • Designed and led the implementation of an email marketing platform with a usage analytics engine and a book publisher online catalog with dynamic PDF catalog generation.
    • Led a development team to implement a new, modern development lifecycle using test integration and development-quality assurance-production-promotion pipelines.
    Technologies: Java, Oracle, PostgreSQL, Mainframe, XSLT, XSL-FO, Spring, Enterprise Java Beans (EJB), IIS, Apache, Resin, Networking, API Integration, Integration, Proof of Concept (POC), IIS SQL Server, Web Architecture, APIs, Linux, eCommerce, Architecture, Startups, System Architecture, API Architecture, Data Strategy, SaaS, Technical Leadership, Third-party Integration, SQL, HTML, Web Development, Leadership, Software Architecture, System Architecture Design, Fintech, REST

Experience

  • Music Search Augmentation
    https://www.premiumbeat.com/royalty-free-music?q=zeppelin

    TASK
    Improve the web search experience for Premiumbeat, a stock music provider, to surface matching available content when customers search for well-known popular names.

    SOLUTION
    Developed an ML-based analytic system, processing daily search stats and using Spotify API and Music Brainz databases to tag offered tracks matching popular artists and songs. As a result, searching for "zeppelin" returns a few dozen classic rock tracks, matching them by the desired style rather than by name.

  • Web Search Content Filtering
    https://www.shutterstock.com/video/search/data-processing

    TASK
    Enable web search results to be reordered based on customers' geo regions, current and seasonal trends, and collaborative filtering.

    SOLUTION
    I led a solution to implement a data analysis pipeline feeding a collaboration filtering ML model to achieve better surfacing of the video content. This improved the first-line click-through rate by 15% and the first-page click-through rate by 30%.

  • Virtual Assistant | General Knowledge Answering
    https://www.cerence.com/news-releases/news-release-details/ask-us-anything-cerence-browse-brings-search-engine-level

    TASK
    Create a system capable of answering virtually any fact-check type question and complement existing embedded car assistants with this capability. Almost single-handedly, I designed, developed, and deployed a POC for such a system. It used a unique process to search for public knowledge and extract an answer to a given question by using an advanced AI model.

    KEY ACTIVITIES
    • Designed a POC solution.
    • Designed and coded two microservice APIs, using Node.js and Python running on Azure Functions (serverless).
    • Integrated with Google and Bing APIs.
    • Developed an API server to host a PyTorch DNN model.
    • Deployed all components into Azure Cloud, using Web Apps, Functions, VM, API Management, and Insights.
    • Developed and deployed a BDD test suite.
    • Set up a statistics data stream to a Power BI dashboard.

  • Database Migration | Two Billion+ Assets
    http://www.shutterstock.com

    TASK
    Replace the business backbone database holding two billion+ assets with no downtime for the company.

    SOLUTION
    Designed and led a no-downtime production migration from MySQL to a new Cassandra-based media database with the following criteria:
    • Two billion assets, scalable to 10 billion.
    • Candidate selection through POC.
    • Peak performance of 120,000 TPS.
    • Geo-distributed.
    • No migration downtime.

  • Upscaled Video Detection Model

    TASK
    Conduct R&D research for a system to detect videos shot in lower resolution and later upscaled by software.

    SOLUTION
    Conducted research and built a POC service capable of performing this task.

    KEY ACTIVITIES
    • Ran paper research and a series of experiments.
    • Transformed scientific research findings into real-world algorithms.
    • Trained and applied a variety of ML models.
    • Demoed the solution and results to the executive team.

  • Audio Track Instrument Detection System
    http://www.premiumbeat.com

    TASK
    Create a tool that can detect musical instruments in a given soundtrack.

    SOLUTION
    Researched the state of the art and designed a new system using a VGGish model trained on a YouTube-8M dataset. The model has been used as the first stage for transfer learning where a new classification model has been built to classify instruments.

  • Automotive Digital Twin Cloud Platform

    CHALLENGE
    An end-user companion mobile app displaying a car's telemetry should have around 200 ms overall latency for the whole trip: from hardware to IoT cloud to storage to API to mobile app. The traffic comprises one million cars reporting every five seconds, making it 200,000 per second.

    SOLUTION
    Designed and led the development of Azure-based serverless cloud architecture, maximally using power or native cloud streaming components. It provides performance at a great scale with the required reliability for the automotive domain.

  • Blockchain-based Investment Platform

    Engaged as a lead technical architect, leading the design and MVP estimation for a blockchain-based crypto investment platform allowing social content makers to capitalize on their work and for their subscribers to participate in financing new projects.

    Chosen Technology: Blockchain for stake participation and dividends distribution

Skills

  • Languages

    Python, SQL, HTML, Java, XSLT, XSL-FO, JavaScript, CSS, R, Go
  • Libraries/APIs

    Node.js, Protobuf, Spark ML, TensorFlow, PyTorch, React
  • Tools

    Confluence, Lucidchart, Apache, Jupyter, Solr, Microsoft Power BI, DataStax, Git, Azure IoT Hub, IBM Watson, AWS Batch
  • Paradigms

    Web Architecture, Behavior-driven Development (BDD), API Architecture, Microservices, Microservices Architecture, Serverless Architecture, REST, Data Science
  • Platforms

    Azure, Linux, Azure Functions, Amazon EC2, Kubernetes, Databricks, Oracle, Docker, Amazon Web Services (AWS), Zendesk, AWS Lambda, Blockchain
  • Storage

    Cassandra, Redis, NoSQL, PostgreSQL, Elasticsearch, IIS SQL Server
  • Other

    Networking, Distributed Systems, Fusion, Serverless, API Integration, Integration, Proof of Concept (POC), MVP Design, Solution Design, APIs, Cloud, IT Strategy, Startups, Architecture, System Architecture, Data Strategy, SaaS, Technical Leadership, Third-party Integration, Web Development, Software Architecture, System Architecture Design, Search, Solution Architecture, Data Engineering, AWS, Voice, Machine Learning, Google Search Appliance, Artificial Intelligence (AI), Enterprise Java Beans (EJB), Big Data Architecture, Videos, Deep Learning, Audio Processing, eCommerce, Computer Vision, Leadership, Information Retrieval, Fintech, Internet of Things (IoT), Digitalocean, Natural Language Understanding (NLU), Zuora, Knowledge Management, Mainframe, IIS, Resin, Natural Language Queries, Research, POC, Pitch Preparation, Cost Estimation, Cryptocurrency Payments
  • Frameworks

    Spark, Spring, Hadoop
  • Industry Expertise

    Automotive

Education

  • Master's Degree in Computer Engineering
    1989 - 1994
    Fedkovych National University - Chernivtsi, Ukraine

Certifications

  • Certified Kubernetes Application Developer (CKAD)
    JUNE 2019 - PRESENT
    Linux Academy
  • Data Science
    MARCH 2015 - PRESENT
    Coursera
  • Microsoft Certified Professional
    JUNE 2000 - PRESENT
    Microsoft

To view more profiles

Join Toptal
Share it with others