Agentic AI Workflow @ Postman
End-to-end multi-agent system for semantic code retrieval
Architected a CrewAI + LangChain pipeline with ChromaDB vector search, reducing agent query latency by 40% and indexing 10k+ code embeddings.
AI Engineer & Data Scientist crafting intelligent systems with deep learning, NLP, and multi-agent architectures.
MS @ UTS · MS in CS @ IU · Former AI Intern @ Postman · Based in Sydney · Photography on the side · Learning Japanese
Projects spanning AI, deep learning, and data engineering.
End-to-end multi-agent system for semantic code retrieval
Architected a CrewAI + LangChain pipeline with ChromaDB vector search, reducing agent query latency by 40% and indexing 10k+ code embeddings.
Multi-task learning with Mixture-of-Experts routing
Resolved cross-task gradient conflicts using MMoE architecture, boosting multi-task prediction accuracy by 4% over Shared Bottom baseline.
Technical deep-dives, build logs, and occasional reflections.
Moments captured between the code.