Senior Data Scientist / ML Engineer

- Implemented LLM-based notifications, action recommendations and predictive behavior models for a personal CRM app

- Built ML models to predict real-time availability for millions of products, resulting in operational efficiency and cost savings - Developed a new delivery time prediction system composed of multiple submodels for all order lifecycle stages, with automated pipelines for data processing, training, and real-time inference. - Initiated the development of an internal LLM-powered chatbot to automate data requests, establishing a self-service reporting tool for business teams.

- Developed predictive models using LSTM, ARIMA, and XGBoost algorithms to forecast demand, detect malfunctions, and optimize prices in the utilities sector. - Created a cutting-edge wildfire detection system using CNNs and Yolo deep learning techniques, achieving 96% accuracy and generating alerts within 30 seconds. - Implemented NLP techniques for text classification and knowledge graph construction from unstructured nutrition data, reducing processing time by 10x through document embedding and entity recognition. - Effectively communicated actionable insights to both technical and non-technical audiences through A/B tests, KPIs, and statistical reports. - Successfully led and mentored a 3-person team in testing, scaling, and delivering Data Science products to meet business requirements.

- Implemented hardware acceleration for Python ML libraries (FPGA, GPU), resulting in a 20x speed boost and significant cost savings. - Collaborated with global fintech clients to provide data-driven insights for credit scoring, fraud detection, and stock prediction. - Designed and trained various data science solutions, including statistical models for tabular data and neural networks for CV and NLP applications, ensuring high performance and scalability in cloud-based deployments. - Led the successful submission of our ML benchmarks accelerator, partnering with industry leaders such as Google and Nvidia.

- Automated database entry and enabled large-scale geospatial data analysis through visualization and statistical analysis - Improved event detection efficiency by 42% compared to traditional methods, by building machine learning techniques

- Developed a custom data analysis tool for medical information, enabling efficient trend detection and data visualization