AI Engineer · Ho Chi Minh City
I'm Bac — an AI Engineer working on software-defined vehicles. I build computer-vision and edge-AI pipelines, virtual vehicle simulation, and multi-agent systems, with a research background in speech, vision, and NLP. Here's my work, and what I've learned shipping it.
AutoNxt AI · Kaizenics
A domain-agnostic agentic AI platform — multi-agent orchestration that adapts across domains. Built at AutoNxt AI for Kaizenics, with a software-defined-vehicle application running virtual cars on RemotiveLabs ECUs with Android Automotive and CARLA.
AutoNxt AI · digital.auto
A child-presence safety reminder that helps prevent children from being left unattended in a vehicle — built at AutoNxt AI with digital.auto.
Research @ A*STAR I²R, Singapore
A hybrid Whisper-encoder + LLaMA-decoder ASR system for Malay–English code-switching, trained with Noisy Student Training and teacher–student pseudo-labeling for low-resource robustness.
Reduced WER from 34% → 28% on the CS-ASR benchmark
Hands-on guide to self-hosting open-weights LLMs with vLLM: install, serve an OpenAI-compatible API, quantize, benchmark, and manage VRAM.
Build a typed MCP server in Python, run it over stdio and HTTP, wire it into Cursor, and drive it from a custom client and an OpenAI-compatible model.
What I learned building a Whisper + LLaMA speech recognizer for Malay–English code-switching — where the WER actually came from, and what didn't help.
A hands-on, current (2026) path for taking a PyTorch CV model to ONNX and a TensorRT engine: export, parity, FP16/INT8 build, and latency gating.