Yehor – Python, Django, React

Tool that provides customized, secure, and context-aware AI solutions to get advanced insights from across the business instantly accessible and actionable. It works as a computational notebooks that allow entering commands in human language to be interpreted by an AI.

• Integrated Plate JS to build notebook functionality: a rich text editor, support for the Slash command, storing data in the database and more;
• Enhanced AI features according to new requirements, including new prompts, branching logic, better parsing and error handling;
• Developed file upload feature, supporting several file formats, validation, and handling of malformed data;
• Implemented a custom table component and relevant API logic with pagination, filtering, sorting, and dynamic data support;
• Optimized the app performance by utilizing caching and reducing the number of requests to the API.

App showing data demographics per place in the US and Canada. It allows users to draw on the map, check data for the drawn territory, and check where people can reach by walk/car/etc.

• Led the end-to-end project lifecycle with minimal input, ensuring high-quality deliverables;
• Designed and implemented a new database schema for Canadian data, ensuring scalability and efficiency;
• Led the migration from MongoDB to PostgreSQL for multiplayer feature, designing and implementing database schemas;
• Implemented client-side and business logic to generate data-intensive PDF reports, ensuring consistent outputs independent of user screen dimensions;
• Developed a psychographic insights feature, enabling users to gain deeper lifestyle-based insights into selected geographic areas.

The product aims to help journalists write articles, especially based on other materials, by utilizing generative AI capabilities. Another feature is connected with various automation tools for a company to repair articles: linking to rules from reference books, searching, answering user questions, etc.

• Integrated LLM-based solutions and vector search to enhance content retrieval and search efficiency across large datasets;
• Designed and implemented pipelines using Temporal and Kafka for persistent, scheduled data processing, leveraging Regex and LLM evaluation for accurate data extraction from external APIs;
• Developed ingestion pipelines to preprocess and index external data into MongoDB and Typesense, optimizing it for advanced search and retrieval tasks;
• Build the RAG system that integrates 3 data sources to provide users with answers based on the stored data.

Platform for performing audio and video recording transcription, transcription editing, and analysis. It aims at personal and corporate users. The most significant users are the Norway State Library and the Norway Police.

• Developed a public API with Python and Flask to provide transcription functionality to corporations, driving user acquisition and product engagement;
• Optimized speech-to-text pipeline, making it take half the length of the audio clip;
• Designed and integrated a high-performance search functionality for transcriptions by leveraging ElasticSearch for fast querying;
• Streamlined the deployment pipeline using CI/CD automation, reducing release times by 90%.

Management and versioning tool for researchers in healthcare, featuring a DICOM-compatible image library and a robust user management system. It facilitates the efficient handling of training data and collaborative research.

• Developer core API endpoints and business logic with Python and Flask to support application features;
• Implemented an ability to upload and manipulate DICOM files;
• Integrated authentication and authorization from scratch to provide protected access to resources in the app;
• Configured deployment of the API to AWS with the support of development and production environments.