I'm a Software Architect with 14+ years of experience designing and building scalable, resilient, secure, and cloud-native enterprise systems across Banking, FinTech, Telecom, Insurance, and Enterprise Software.

My engineering background is rooted in Backend Engineering, Distributed Systems, Microservices, Event-Driven Architecture, and Cloud-Native Platforms.

Today, I'm extending that foundation into AI Engineering and Enterprise AI Architecture, focusing on how Large Language Models, Retrieval-Augmented Generation, AI Agents, and Cloud AI capabilities can be integrated into reliable production systems.

My focus: bridging Software Engineering + Cloud Architecture + AI Engineering.

I am building a connected technical ecosystem around AI Engineering, Cloud Architecture, Backend Engineering, and Enterprise AI Architecture.

                    Mihir Jha
                       │
        ┌──────────────┼──────────────┐
        │              │              │
      Blog          Handbook       LinkedIn
        │              │              │
        │              │              └── Discussion & Discovery
        │              │
        │              └── Structured Technical Reference
        │
        ├── Deep Technical Articles
        ├── Architecture Deep Dives
        └── Production Engineering
                       │
                       ▼
                GitHub Projects
                       │
                       ▼
                 Implementations

I'm currently focused on building expertise across:

• 🤖 Large Language Models (LLMs)
• 🔍 Retrieval-Augmented Generation (RAG)
• 🧠 AI Agents & Agentic AI
• ☁️ Cloud-Native AI Platforms
• 📦 AI-Powered Microservices
• 🏗 Enterprise AI Architecture
• 📊 AI Evaluation & Observability
• 🔄 MLOps & LLMOps
• 🔐 AI Security & Governance
• 🚀 Production AI System Design

The broader engineering journey is:

Software Engineering
        ↓
Cloud Engineering
        ↓
AI Engineering
        ↓
AI Systems Engineering
        ↓
Enterprise AI Architecture

My AI content and learning journey is organized around three complementary tracks.

Learn AI

A practical journey connecting:

• Machine Learning
• Deep Learning
• Foundation Models
• Large Language Models
• Prompt Engineering
• RAG
• AI Agents
• Cloud AI
• Production AI Engineering

The goal is to help backend engineers understand how AI capabilities become part of modern software systems.

Understand AI

A hands-on exploration of the internal components behind modern AI systems.

Areas include:

• Neural Networks
• Transformers
• LLM Internals
• AI Training
• AI Inference
• PyTorch
• TensorFlow / Keras
• Performance & Optimization

The goal is to understand what happens underneath the abstractions.

Architect AI

A production-focused architecture journey exploring:

• Enterprise AI Architecture
• RAG Systems
• AI Gateways
• Agentic AI
• AI Platforms
• Observability
• LLMOps
• AI Security
• Governance
• Distributed AI
• Inference Infrastructure
• AI FinOps

Together:

Learn
  ↓
Understand
  ↓
Build
  ↓
Architect
  ↓
Operate
  ↓
Optimize

With 14+ years of experience, I've worked on designing and delivering:

• Enterprise Java Platforms
• Cloud-Native Applications
• Microservices Architecture
• Distributed Systems
• Event-Driven Architectures
• High-Throughput Backend Systems
• API Platform Engineering
• Infrastructure as Code
• DevOps Automation
• Secure Enterprise Applications
• Production System Design

• 🏦 Banking
• 💳 FinTech
• 📡 Telecom
• 🛡 Insurance
• 🏢 Enterprise Software

• Java
• Kotlin
• Python
• SQL

• Spring Boot
• Spring Cloud
• Micronaut
• Hibernate / JPA
• REST APIs
• Reactive Programming
• Domain-Driven Design (DDD)
• Microservices
• Event-Driven Architecture

• Amazon Web Services (AWS)
• Microsoft Azure
• Google Cloud Platform (GCP)
• Kubernetes
• Docker
• Terraform
• CloudFormation

• Jenkins
• ArgoCD
• Bitbucket Pipelines
• CI/CD
• Infrastructure as Code
• Containerized Deployments

• Apache Kafka
• RabbitMQ
• Redis
• MongoDB
• PostgreSQL
• Oracle
• MariaDB
• Aerospike

• OAuth2
• JWT
• Secure API Design
• Secret Management
• Identity & Access Control

• Grafana
• Graylog
• Monitoring & Logging
• Distributed Tracing

Currently building expertise across:

• Machine Learning
• Deep Learning
• Neural Networks
• TensorFlow
• Keras
• PyTorch
• Scikit-learn
• Hugging Face Transformers
• Prompt Engineering
• RAG
• Vector Databases
• AI Agents
• Agentic AI
• AI Evaluation
• MLOps Foundations
• LLMOps
• AI System Design

Validated expertise in designing and architecting secure, scalable, reliable, and highly available solutions on Google Cloud.

Foundational certification covering Azure cloud concepts, core services, architecture, security, and cloud economics.

Completed the IBM AI Engineering Professional Certificate covering areas such as:

• Machine Learning
• Deep Learning
• Neural Networks
• TensorFlow
• Keras
• PyTorch
• Computer Vision
• Model Development
• Model Deployment
• AI Engineering Practices

I continue to expand this foundation through practical work in:

• Cloud AI
• RAG
• AI Agents
• LLMOps
• Enterprise AI Architecture
• AI System Design

I enjoy documenting what I learn through:

• Technical articles
• Architecture deep dives
• Engineering perspectives
• AI system design
• Production patterns
• Practical implementations

https://enterpriseai.blog.mihirkjha.com/

https://enterpriseai.handbook.mihirkjha.com/

https://www.linkedin.com/newsletters/enterprise-ai-engineering-7479222208079319041/

My technical content focuses on:

• 🤖 AI Engineering
• 🧠 Large Language Models
• 🔍 RAG & Advanced Retrieval
• 🤖 AI Agents & Agentic AI
• ☁️ Cloud AI Architecture
• 🚀 Production AI Systems
• 📊 MLOps & LLMOps
• ⚙️ Backend Engineering
• 🏗 System Design
• 🌐 Cloud-Native Architecture
• 📦 Enterprise Software Architecture
• 🔐 AI Security & Governance
• 📈 AI Observability & Evaluation

My GitHub work spans:

• 🤖 AI Engineering Projects
• 🧠 LLM Experiments
• 🔍 RAG Systems
• 🤖 AI Agents
• ☁️ Cloud AI Architecture
• 📦 AI Microservices
• ⚙️ Spring Boot & Java
• ☁️ Cloud-Native Systems
• 🏗 Distributed Systems
• 🚀 DevOps & Infrastructure as Code
• 📚 Technical Notes
• 🧪 AI Experiments
• 🎯 System Design Examples

Build systems, not just components.

I believe successful AI systems require much more than powerful models.

They require:

• Strong Software Engineering
• Scalable Cloud Architecture
• Reliable Infrastructure
• Continuous Evaluation
• Observability
• Security by Design
• Responsible AI Practices
• Cost Awareness
• Continuous Learning

A useful mental model is:

Model
  +
Context
  +
Retrieval
  +
Tools
  +
Application Logic
  +
Security
  +
Observability
  +
Infrastructure
  =
Production AI System

My goal is to bridge traditional software and cloud engineering with modern AI engineering and build practical understanding of how to design systems that are:

• Intelligent
• Scalable
• Secure
• Observable
• Reliable
• Cost-aware
• Maintainable
• Production-ready

The long-term direction is:

Cloud AI Architect → Enterprise AI Architect

• Advanced RAG Architectures
• AI Agents & Agentic Workflows
• Model Context Protocol (MCP)
• AI Evaluation
• AI Observability
• LLMOps
• Enterprise AI Platform Design
• Cloud AI Services
• Production AI Patterns
• AI Security & Governance
• AI Infrastructure & Inference

✅ IBM AI Engineering Professional Certificate
✅ Google Cloud Professional Cloud Architect
✅ Microsoft Azure Fundamentals
✅ Production AI Foundations
🔄 Advanced RAG Systems
🔄 AI Agents & Agentic Workflows
🔄 Model Context Protocol
🔄 LLMOps & AI Observability
🔄 Enterprise AI Platform Design
🎯 Cloud AI Architect

The roadmap will continue evolving as the technology landscape changes.

https://www.linkedin.com/in/mihirkrjha/

https://enterpriseai.blog.mihirkjha.com/

https://enterpriseai.handbook.mihirkjha.com/

https://www.linkedin.com/newsletters/enterprise-ai-engineering-7479222208079319041/

Outside of work and technology, I enjoy:

• 📖 Learning emerging technologies
• ✍️ Writing technical content
• 🏗 Exploring distributed system design
• 🚀 Following AI innovations
• ♟ Playing chess
• 🌌 Exploring space science