Welcome to ppippi-dev Blog

Hello! I’m a developer with hands-on experience across MLOps, AI, and Cloud technologies.

About Me

I’m particularly passionate about deploying and operating machine learning systems in production environments, building stable and scalable AI infrastructure in cloud-native settings. This blog is where I share not just theoretical knowledge, but practical experiences and problem-solving processes from real projects.

Blog Philosophy

This blog is more than just a collection of technical documentation—it’s a space for recording real-world problems encountered during development and their solutions. By transparently sharing my trial-and-error processes and learning journey, I aim to provide practical help to other developers facing similar challenges.

Core Values:

  • Practicality: Work-focused content that can be immediately applied to real projects
  • Depth: Covering not just surface-level usage, but underlying principles and best practices
  • Accuracy: Reliable content based on verified information and actual experience
  • Continuous Improvement: Updating and improving content to match technological changes

Main Topics

MLOps & AI Infrastructure

Covering the entire process of deploying and operating machine learning models in production environments. Deep dives into model serving, monitoring, A/B testing, retraining pipelines, and other essential production skills.

LLMOps & Agent Development

Exploring the latest LLM technologies and AI Agent development. Sharing real implementation cases and architecture design experiences using various frameworks like OpenAI API, LangChain, and Google ADK.

Cloud & DevOps

Sharing infrastructure building experiences on major cloud platforms including AWS, GCP, and Azure. Covering Infrastructure as Code using Kubernetes, Docker, Terraform, and CI/CD pipeline construction.

Data Engineering

Covering core data engineering topics including data pipeline construction, ETL/ELT processes, and data quality management.

Tech Stack

Infrastructure & Cloud:

  • Kubernetes, Docker, Helm
  • AWS (ECS, EKS, Lambda, S3, etc.)
  • GCP (GKE, Cloud Run, BigQuery, etc.)
  • Terraform, ArgoCD

ML/AI & Data:

  • Python, TensorFlow, PyTorch
  • Triton Inference Server, MLflow
  • Apache Airflow, Apache Spark
  • Pandas, NumPy, Scikit-learn

LLM & Agent:

  • OpenAI API, Anthropic Claude
  • LangChain, Google ADK
  • Vector Databases (Pinecone, Weaviate)
  • Prompt Engineering & Fine-tuning

Development & Monitoring:

  • Git, GitHub Actions, GitLab CI
  • Prometheus, Grafana
  • PostgreSQL, Redis
  • FastAPI, Flask

Target Audience

This blog will be helpful for:

  • Developers interested in MLOps/LLMOps fields
  • Engineers deploying and operating machine learning models in production
  • DevOps engineers building infrastructure in cloud-native environments
  • Anyone seeking to understand the full lifecycle of AI/ML systems

Content Quality Standards

All posts strive to meet the following criteria:

  1. Experience-Based: Only writing about content that has been actually implemented and tested
  2. Reproducibility: Providing step-by-step guides with code examples
  3. Problem-Solving Focused: Clearly explaining why this technology is used and what problems it solves
  4. Best Practices: Reflecting industry standards and best practices
  5. Continuous Updates: Keeping content up-to-date with technological changes

Contact & Collaboration

Feel free to reach out for technical questions, feedback, or collaboration proposals.

Disclaimer

All content on this blog is based on my personal learning and experience and does not represent the official position of any company or organization I’m affiliated with. While I strive for accuracy in all content, please feel free to provide feedback if you find any technical errors or areas for improvement.

I hope this blog helps with your learning and development. Let’s build a growing tech community together!

Thank you!