Shipping
Intelligence.
Full-stack AI Product Engineer specializing in RAG architectures, LLM orchestration, and intuitive human-AI interfaces.
View Deployments
Bridging Models
& Markets.
I don't just "use" AI; I build products where AI is the core engine. My focus is on **LLMOps**—ensuring that models are not just impressive in a notebook, but reliable, fast, and cost-effective in production.
From prompt engineering and fine-tuning to vector database optimization, I create the infrastructure that makes AI feel like magic.
Capabilities
LLM Orchestration
Expertise in LangChain, LlamaIndex, and AutoGen for building complex agentic loops.
Vector Infra
Pinecone, Weaviate, and pgvector for semantic search.
Frontend AI
Building streaming interfaces with Next.js, Vercel AI SDK, and Framer Motion.
Inference
Deploying with Modal, Replicate, and vLLM.
Fine-tuning
LoRA and QLoRA for domain-specific models.
Selected Work
Nexus-1 Editor
An AI-native text editor that uses autonomous agents to research, fact-check, and suggest citations in real-time as you write.
DocuMind Enterprise
Search across 100k+ internal documents with sub-second latency using a custom hybrid search (BM25 + Dense Embeddings).