AI Systems Development

Exploring advanced deep learning architectures, hardware-aware optimizations, and performant AI deployments.

Work Focus

Transformers Multi-Modal Learning Reinforcement Learning Neural Architecture Search MLOps CUDA Optimization Generative AI Edge Computing Robot Learning

Featured Projects

Efficient LLM Fine-tuning with LoRA and QLoRA

An implementation of efficient fine-tuning techniques for large language models, focusing on parameter-efficient methods like LoRA and QLoRA.

PyTorch Transformers bitsandbytes PEFT
Read More

Retrieval-Augmented Generation (RAG) for Knowledge-Intensive NLP Tasks

A state-of-the-art RAG pipeline combining dense retrieval with generative language models.

PyTorch Hugging Face FAISS LangChain
Read More

Advanced Image Classification

Implementation of state-of-the-art image classification using Vision Transformers (ViT).

PyTorch Hugging Face TensorFlow
Read More

Optimized Stable Diffusion Pipeline

High-performance Stable Diffusion implementation with custom attention mechanisms.

PyTorch diffusers xFormers CUDA
Read More

End-to-End MLOps Pipeline with Kubernetes

Production-grade MLOps infrastructure with automated training and deployment pipelines.

Kubernetes MLflow Kubeflow
Read More

High-Throughput LLM Serving

Optimized serving system for large language models with dynamic Kubernetes scaling.

vLLM Triton CUDA Graphs Ray
Read More