Skip to content
View andreimerfu's full-sized avatar
9 followers · 2 following

Achievements

Achievement: Pull Sharkx2Achievement: YOLOAchievement: Arctic Code Vault Contributor

Achievements

Achievement: Pull Sharkx2Achievement: YOLOAchievement: Arctic Code Vault Contributor

Block or report andreimerfu

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
andreimerfu/README.md

Waving Hand Hey there, I'm Andrei Merfu

Typing SVG

Portfolio Twitter Email GitHub followers

🚀 About Me

Coding

  • 🏗️ Creator of pLLM - High-performance LLM Gateway for scalable AI applications
  • 📍 Based in Bucharest, Romania 🇷🇴
  • 💼 Senior Software Engineer specializing in Cloud Architecture and Distributed Systems
  • 🔧 Building enterprise-grade solutions with AWS, Kubernetes, and Terraform
  • 💰 Building cost-effective infrastructure for startups - Optimizing cloud spend while maintaining performance
  • 🛡️ Security & Compliance Expert - Ensuring infrastructure is ISO 27001 and SOC 2 compliant
  • 📝 I regularly write technical articles on merfu.me/articles
  • 🎯 Currently focused on LLM Infrastructure and AI/ML Operations
  • 💡 Open to collaborating on innovative AI/ML projects

🎯 Featured Project: pLLM

pLLM is a cutting-edge, high-performance LLM Gateway designed to simplify and accelerate Large Language Model deployments at scale.

✨ Key Features

  • ⚡ Ultra-low latency - Sub-millisecond overhead for LLM requests
  • 🔄 Multi-provider support - Unified API for OpenAI, Anthropic, Azure, and more
  • 📊 Built-in observability - Real-time metrics and comprehensive logging
  • 🛡️ Enterprise-ready - Production-grade security and reliability
  • 🚀 Kubernetes-native - Seamless integration with cloud-native infrastructure
  • 📈 Auto-scaling - Dynamic resource allocation based on demand

💻 Tech Stack & Skills

🚀 Languages

Go Ruby Rust Python TypeScript

☁️ Cloud & Infrastructure

AWS Azure Hetzner Kubernetes Terraform Docker Helm

🎨 Frameworks

Rails Fiber Astro Next JS

🗄️ Databases

PostgreSQL Redis MongoDB Cassandra DynamoDB InfluxDB

🔧 DevOps & Monitoring

GitLab CI GitHub Actions ArgoCD Prometheus Grafana OpenTelemetry Datadog

📊 GitHub Analytics

GitHub Stats Top Languages
GitHub Streak

🏆 Achievements & Certifications

AWS Certified CKA Terraform Associate

ISO 27001 SOC 2

📚 Latest Projects

📈 Contribution Graph

Contribution Graph

🤝 Let's Connect!

I'm always interested in collaborating on innovative projects, especially in the AI/ML and cloud infrastructure space.

Whether you're looking for technical expertise, want to discuss pLLM, or just want to connect, feel free to reach out!

View Projects Read Articles View Resume
Profile Views

Made with Love Powered by Coffee

Footer

Pinned Loading

  1. pllm pllm Public

    High-performance LLM Gateway built in Go - OpenAI compatible proxy with multi-provider support, adaptive routing, and enterprise features

    Go 2 1

  2. pllm-website pllm-website Public

    Official website and documentation for pLLM - High-performance LLM Gateway

    Astro

  3. rails-saas-kit rails-saas-kit Public

    Enterprise-grade Ruby on Rails SaaS starter kit with multi-tenancy, Stripe payments, and modern UI

    Ruby

  4. terraform-hcloud-immich terraform-hcloud-immich Public

    This Terraform module deploys a complete Immich instance on Hetzner Cloud, optimized for family use with minimal operational costs. Features unlimited photo storage via Backblaze B2 integration.

    HCL