👋 About Me
🔭 I’m currently working on
Production-grade Generative AI systems at Adobe
Retrieval-Augmented Generation (RAG) pipelines for document intelligence
Agentic AI applications with multi-step reasoning, tool use, and memory
LLM evaluation frameworks for faithfulness, grounding, relevance, and retrieval quality
👯 I’m looking to collaborate on
Open-source RAG frameworks, agent orchestration systems, and GenAI tooling
LLM evaluation, benchmarking, and reliability research
Document AI, enterprise search, and knowledge-intensive AI systems
🤝 I’m looking for help with
Scaling agent-based systems in production
Improving long-context retrieval and reasoning
Better offline and online evaluation strategies for GenAI systems
🌱 I’m currently learning
Advanced agent architectures and planning-based systems
LLM inference optimization and cost-efficient serving
Trust, safety, and evaluation techniques for real-world GenAI products
💬 Ask me about
RAG design and optimization
Prompt engineering for production systems
Agentic AI workflows and tool-using agents
LLM evaluation metrics and GenAI reliability
Document intelligence, search, and retrieval systems
⚡ Fun fact
I’ve been building retrieval and document AI systems since before “RAG” was a buzzword
