🚀 I'm currently working on
- Building production-ready RAG applications with LlamaIndex and open-source LLMs
- Developing full-stack AI systems with FastAPI and React
- Exploring LLM fine-tuning techniques for domain-specific applications
👯 I'm looking to collaborate on
- GenAI and LLM-powered applications (RAG systems, AI agents)
- Full-stack AI/ML projects combining backend and frontend
- Open-source AI/ML initiatives
🤝 I'm looking for help with
- Advanced LLM fine-tuning strategies (LoRA, QLoRA, PEFT)
- Scaling AI applications with microservices architecture
- Production-level deployment and MLOps best practices
- Advanced prompt engineering techniques
🌱 I'm currently learning
- Model fine-tuning and custom training pipelines
- Advanced RAG architectures and agent orchestration
- Docker and Kubernetes for ML deployment
- System design for scalable AI systems
💬 Ask me about
- Building RAG systems with LlamaIndex and vector databases
- Full-stack AI development with FastAPI and React
- Working with open-source LLMs (Llama, Mistral)
- Implementing semantic search and document processing
- Getting started with AI/ML development
⚡ Fun fact — I went from training simple ML models to deploying production GenAI systems faster than most people learn to prompt ChatGPT! Also, my code compiles better at 2 AM ☕🌙
