← Back to Students
Bluma G.
Bio
Highly analytical software engineering graduate with deep system-level understanding and strong problem-solving abilities. Skilled in independent self-learning, tackling complex challenges, and adapting quickly to new technologies. A dedicated team player with a strong work ethic, high motivation, and a constant drive for excellence.
Skills
Python
C++
ONNX
PyTorch
OpenVINO Toolkit
Operator Implementation
AI Inference Optimization
Quantization
Tensor Operations
Git/GitHub
Ubuntu/Linux
Bootcamp Project
Model optimization and performance contributions
Mentored by: Mobileye
Embedded Systems Bootcamp 2025 (Embedded)
Responsibilities:
Quantization & performance analysis of AI inference models across CPU/GPU
Benchmarking latency, throughput, memory usage, and system-level behavior
Researching accuracy vs performance trade-offs in quantized models
Implemented the full aten::quantile operator in the OpenVINO PyTorch Frontend — including operator translation, shape-inference logic, broadcasting-safe reshaping, all interpolation modes, support for dim=None and keepdim, NaN-propagation handling, performance optimizations (TopK/Gather), and full numerical validation against PyTorch.
Click to enlarge
Additional Projects
Developed a medical clinics network management system based on .NET Core WebAPI and React, including REST APIs for managing appointments, customers, and payments. Data is stored in a SQL database using a dedicated schema. The system includes a work calendar, advanced search, and treatment documentation. Implemented using a modular architecture with Separation of Concerns and dependency injection to ensure flexibility and extensibility.
English Level
Working Proficiency