Hey there, thanks for checking out my GitHub profile!
My name is Bacem, and I'm studying Computer Engineering at McMaster University.
Technical Interests:
- Agentic Systems
- Embodied AI (especially autonomous vehicles)
- AI infrastructure
- LLM inference
- GPU programming
Hobbies:
- Reading
- Soccer
- Swimming
- Rock climbing
- Flying
- Travelling
- Video games
|
Currently working on this project. As the title suggests, building the transformer architecture as presented in the AIAYN paper from scratch in C++ for maximum performance. Tech: C++ |
A C++ path tracer with both CPU and CUDA renderers. Implements recursive ray scattering, antialiasing, gamma correction, depth-of-field camera controls, and multiple material types. Tech: C++, CUDA, NVIDIA Nsight |
|
A benchmark for parameter-efficient fine-tuning of a 7B language model on BBC XSum summarization, comparing LoRA and QLoRA across quality, training time, VRAM usage, and distributed behavior. Tech: Python, PyTorch, Hugging Face, LoRA, QLoRA, Accelerate |
An autonomous hyperparameter tuning framework orchestrated with LangGraph. Parallel worker nodes tune neural-network hyperparameters while an LLM-powered coordinator analyzes results. Tech: Python, LangGraph, PyTorch, Optuna, MLflow, OpenAI API |
|
A minimal retrieval-augmented generation prototype built without high-level orchestration frameworks. Implements parsing, chunking, embeddings, vector search, query rewriting, memory, and generation. Tech: Python, ChromaDB, sentence-transformers, OpenAI API |
A real-time American Sign Language to English translation tool built during York University's CTRL+HACK+DEL hackathon. Uses computer vision and ML to detect ASL gestures. Tech: Python, OpenCV, MediaPipe, TensorFlow, Flask |
