Real-time Football Player Tracking with Computer Vision

• Developed ML Miners on the Bittensor network for Tao and dTao cryptocurrency.
• Managed a team of ML developers on Subnet 44 “Scorevision”.
• Achieved first place consistently by training and optimizing computer vision models.
• Implemented real-time tracking of football players and pitch key points from video footage.
• Trained Yolo models for miners and Clip for validators.

• Developed NLP pipeline for generating videos from URLs.
• Implemented a conversation quality metric using Python and FastAPI.
• Deployed solutions via Docker on private Amazon servers.
• Developed an internal user interface dashboard in JavaScript.
• Fine-tuned GPT-neo for conditional text generation.

In the corporate sector, text data flows swiftly, emanating from diverse sources in various formats, destined for multiple endpoints and actions. This continuous stream of data necessitates management through structuring, making it easy to interpret and analyse, and ultimately directing it to the appropriate user or applying the insights obtained. I utilised several large language models (LLMs) streamline and enhance this process:

• A question-answering LLM, enabling users to inquire about the content of each document within the flow.
• A summarization LLM, offering a concise overview of each document.
• An NLP model for sentiment analysis, determining the sentiment of each document.
• An NLP model that calculates an absolute similarity score among all documents.
• Clustering, which groups similar documents together and simultaneously identifies outlier documents.

• Collected and preprocessed data to build a time prediction model that improved the accuracy of rendering job estimates.

• Designed and implemented a visual predictive model using synthetic data for internal research.

• Built a sentiment analysis tool to assess user feedback and created a recommendation system based on user behaviour patterns.

Led a team of 3 developers in designing and maintaining RuBackup’s software ecosystem.

Designed and implemented a modular Python library for backup integrations, now published on PyPi.

Released the first stable version of the web interface and REST API for RuBackup’s backup control system.

Developed and deployed an autoregressive model using statsmodels to predict remaining storage capacity.

Formalised internal coding standards, GitLab practices, and documentation processes to improve code quality and maintainability.