Hello 👋 I'm Hao (Howard) Hoang, a Senior AI Researcher & Engineer. I specialize in LLM systems, AI engineering, agentic workflows, and real-world machine learning applications.
Daily insights on LLM systems, AI engineering, agentic workflows, and real-world machine learning.
I write about:
My work focuses on the intersection of research and engineering, turning cutting-edge papers into production-ready AI systems.
I help:
If you want to level up in AI one day at a time, you're in the right place.
📬 AI Interview Prep Newsletter
September 2025 – Present
Befoundr
Researched and integrated state-of-the-art LLMs, RAG, and agentic AI patterns into productivity chatbots for founders. Designed knowledge retrieval pipelines and multi-step reasoning workflows for investor-focused insights. Consulted on AI architecture, SoTA model selection, prompt engineering, and LLM system design.
October 2023 – Present
Spartan
Built and deployed agentic AI pipelines combining LLMs, RAG (GraphRAG, LightRAG, PathRAG), and vector search for real-world applications. Designed prompt engineering patterns for multi-step reasoning, classification, summarization, and code review automation. Fine-tuned and benchmarked LLMs for domain-specific tasks (coding, PDF parsing, technical diagram understanding). Led AI knowledge-sharing sessions internally; advised on team AI strategy and candidate hiring.
October 2023 – March 2025
J.D. Power
Designed end-to-end RAG pipelines using LangChain and LlamaIndex. Built structured extraction systems for thousands of complex automotive incentive PDFs. Built and operated full backend + ML infra on GCP, Kubernetes, Terraform, Helm. Designed high-reliability systems for large-scale batch inference & parsing. Integrated Azure Document Intelligence with custom OCR + NLP pipelines. Improved accuracy across highly variable OEM document formats (Toyota, Ford, Hyundai, VW…).
January 2023 – December 2023
Viettel Big Data Analytics Center
Built recommendation systems (collaborative filtering, content-based, REC-VAE for TV360) and developed ETL pipelines with Pentaho and PySpark for large-scale data processing.
January 2022 – January 2023
Kratos Defense and Security Solutions
Focused on time series analysis, conducting motif discovery, anomaly detection, and time series summarization using Matrix Profile techniques.
September 2019 – September 2022
INSA Toulouse
Applied advanced ML (SVM, Random Forest, Neural Networks) and deep learning techniques (Autoencoders, GANs) for anomaly detection and conducted signal processing research.
🚀 Follow me on LinkedIn (45.8K+ followers), subscribe to my Substack (5.5K+ subscribers), or reach out via email at email. Always open to discussing AI, LLMs, and new opportunities!