Building production-grade AI systems from 0 → 1
- Founding AI Engineer building end-to-end AI platforms across LLMs, backend systems, and infrastructure
- Currently developing multi-agent LLM systems (LangChain + MCP) for spacecraft design and supply-chain intelligence
- Full ownership from architecture → development → deployment (on-prem and cloud)
AI Systems
- Multi-agent LLM orchestration (LangChain, tool-calling, reasoning systems)
- Local and cloud inference (TensorRT, AWS SageMaker, GPU optimization)
Backend & Real-Time Systems
- FastAPI, WebSockets, event-driven microservices
- High-performance APIs for AI workflows
Full-Stack Applications
- React / Angular production applications
- AI-integrated user experiences
Infrastructure & DevOps
- Kubernetes, Helm, CI/CD (GitHub Actions)
- On-prem and cloud hybrid deployments in secure environments
- AAAI Symposium Series (2024) — Edge AI and efficient deep learning systems
- SOICT 2023 — Event-based vision and CNN optimization
- Focus: privacy-aware computer vision and edge intelligence
- Built multi-agent AI platforms enabling real-time decision workflows
- Deployed GPU-accelerated LLM systems with optimized inference pipelines
- Designed scalable microservice architectures for production AI systems
- Delivered secure AI deployments in enterprise on-prem environments
Portfolio: https://dat-nguyen.com
Email: thanhdat19022001@gmail.com
LinkedIn: https://www.linkedin.com/in/edric-nguyen/
GitHub: https://github.com/thanhdat1902




