← Back to Students
Tamar P.
Bio
Developer with experience in developing E2E systems through Bootcamp and independent projects. During my training, I demonstrated strong analytical skills, creativity, and precision in executing complex tasks. Highly motivated to integrate into teams as well as work independently, meeting goals under pressure. Looking for my next challenge where I can continue to grow professionally and contribute to success.
Skills
Python
C++
CI/CD
SYCL
Linux
GPU
Bootcamp Project
Extending CPU/GPU LLM inference kernels
Mentored by: Mobileye
Embedded Systems Bootcamp 2025 (Embedded)
Responsibilities:
Contributed GPU implementations for the missing ROLL and SSM_CONV operators in C++/SYCL, including optimized parallel kernels and a custom 4D→3D indexing scheme adapted to GPU hardware limits, achieving ~200–300% performance improvement compared to the previous CPU fallback.
Developed full integration for the Megrez-MoE model: analyzed the HuggingFace structure, mapped all tensors to llama.cpp’s GGUF architecture, and implemented model components according to existing design patterns.
Extended the HuggingFace → GGUF conversion pipeline by adding missing tensor mappings, metadata fields, and architectural parameters, enabling correct conversion, loading, and execution on both CPU and GPU.
Worked extensively with Git, maintained multiple Pull Requests, and contributed code to a large- scale open-source project used worldwide.
Click to enlarge
Additional Projects
Item & User Management API — Secure and Scalable ASP.NET Core Project
Developed a secure and scalable RESTful API designed for managing users and items within an application. The system was built using ASP.NET Core with a clean, modular architecture powered by Dependency Injection. Implemented JWT authentication for robust access control and integrated Swagger for comprehensive API documentation and testing. The project emphasizes maintainability, performance, and future extensibility, reflecting industry-standard best practices.
English Level
Fluent