Huynh Thien Tung

MLOps / Cloud / DevOps Engineer

Building and operating large-scale AI/ML infrastructure — from GPU cluster management and LLM inference optimization to cloud-native DevOps and a security-first mindset.

Ho Chi Minh City, Vietnam huynhthientung.dev@gmail.com LinkedIn GitHub

Experience

VinSmart Future — VinGroup

May 2026 — Present

Middle MLOps Engineer

Large-scale LLM inference infrastructure & AI platform

  • Operate and maintain an enterprise-scale H200 GPU cluster (one of the largest in Vietnam) powering production LLM services
  • Optimize LLM inference throughput and latency using vLLM; own the end-to-end vLLM production serving stack
  • Design GPU resource scheduling, multi-tenant isolation, and capacity planning strategies for high-demand AI workloads
  • Integrate DevSecOps practices across the AI/ML development lifecycle — from model CI/CD pipelines to container image security and supply-chain hardening
  • Collaborate with AI research teams to productionize and reliably serve large language models at scale

ITRVN

Jun 2025 — Apr 2026

Cloud / DevOps Engineer

US-based digital health & wearable medical devices platform

  • Operate EKS clusters and CI/CD pipelines for a US production healthcare platform
  • Built a Golang-based AI tool that detects CVEs and assigns remediation tasks to developers
  • Led AWS account and data migration for a $20K/month production environment
  • Deployed AI/ML workloads on Kubernetes; ran an internal seminar on AI Agentic systems
  • Maintained cloud data pipelines and campaign delivery systems in production
  • Enforced security and compliance practices; optimized performance and cloud cost

Splus Software

Oct 2022 — May 2025

Backend / Cloud / DevOps Engineer

Semiconductor machine control system — outsourcing for a Japanese customer

  • Implemented REST and WebSocket APIs for a next-gen semiconductor control platform
  • Designed serverless AWS architecture and CI/CD pipelines; cut pipeline cost by ~50%
  • Built CI/CD infrastructure on AWS CodeBuild and CodePipeline from HLD to production
  • Automated internal tooling: budget alerts, CloudTrail-to-Slack alerts, and software installers
  • Managed AWS cost and resource hygiene across 6 production accounts
  • Maintained legacy C++ desktop GUI software for machine control reliability

Splus Software

Jun 2022 — Apr 2024

Team Leader

Web scraping system for Japanese real estate and maps data

  • Defined system architecture, crawling strategy, and database schema for the platform
  • Built an extensible, maintainable codebase shared across all crawlers
  • Engineered techniques to bypass rate limiting and bot detection at scale
  • Delivered a scalable system collecting Japanese real estate and maps data

Skills

MLOps & AI Infrastructure
vLLM LLM Serving GPU Cluster Management NVIDIA H200 CUDA Model CI/CD Inference Optimization Multi-tenant GPU Scheduling
Cloud (AWS)
EC2 EKS EFS Lambda S3 RDS Aurora DynamoDB TimestreamDB CloudFront WAF IAM Cognito Pinpoint SQS SNS API Gateway CodeBuild CodePipeline
Containers & Orchestration
Docker Kubernetes (EKS) Helm Karpenter ArgoCD
Infrastructure as Code
AWS CDK (Golang, Python) CloudFormation Pulumi Terraform
CI/CD & Automation
GitHub Actions Jenkins Bash scripting AWS CodePipeline
Languages
Golang Python C++ (11/14/17) Bash JavaScript / Node.js
Databases
PostgreSQL MySQL MongoDB DynamoDB TimestreamDB Aurora RDS
Observability
CloudWatch Prometheus Grafana ELK Stack

Education

University of Information Technology — VNU

Sep 2019 — Nov 2023

Bachelor of Computer Science, specialization in Machine Learning & AI

  • Graduated with Good degree, GPA 87.1%
  • Awarded three merit-based scholarships for academic excellence
  • Full-tuition scholarship for one semester (2021, COVID-19 relief)

Certifications

AWS Solutions Architect — Associate verify ↗
Amazon Web Services
In progress
CKA AWS SAP IELTS 6.0
English
TOEIC — Reading & Listening 690, Speaking & Writing 250