I am an engineer passionate about building scalable AI systems, with a focus on Machine Learning, Deep Learning, and distributed architectures.

This site reflects my journey of exploring core concepts and optimization techniques that drive modern AI systems at scale.

Full-Stack LLM Systems | From Data to Deployment

My background spans multiple areas critical to LLM development, and with my current LLM expertise, I can bring them together to build and optimize the full lifecycle.

• Data Engineering: scalable pipelines, tokenization, dataset curation.
• Model Design: Transformers, Attention Mechanisms, Positional Encoding.
• Pre-Training: distributed training with mixed precision, DeepSpeed, FSDP.
• Fine-Tuning: efficient adaptation with LoRA, QLoRA, quantization.
• Continual Learning: refreshing models with new data and domain adaptation.

Current Deep-Dive Topics

• Transformer Architectures
• Distributed Training at Scale
• GPU Programming and Optimization

Career Progression