From Product Design to AI Engineering: My Journey into the AWS Builder Community
An introduction to my journey from product design to AI engineering, the projects that shaped my path, and what I aim to learn and share with the AWS Builder Community.
Hello, AWS Builders!
I’m Mirza Mahad Baig, an AI Product Engineer from Pakistan with a background spanning product design, software development, and applied artificial intelligence.
My professional journey began in product design, where I spent 6+ years building and designing enterprise SaaS products, complex dashboards, design systems, and user experiences. Working closely with founders, engineers, operations teams, and customers taught me an important lesson: great technology only creates value when it solves the right problem and remains usable in the real world.
That mindset eventually led me deeper into engineering.
Moving from Product Design to AI Engineering
Over the past year, I have expanded my focus into AI and machine learning, particularly:
- Large Language Model applications
- Retrieval-Augmented Generation
- AI agents and workflow automation
- Machine learning and deep learning
- Natural language processing
- Computer vision
- Python and FastAPI
- LangChain and LangGraph
- Vector databases and semantic search
- LLM evaluation and monitoring
- MLOps and cloud infrastructure
One of my most technically challenging projects was CardioScan AI, a deep-learning system developed to assist with coronary artery disease detection using myocardial perfusion imaging. The project involved medical-image preprocessing, augmentation, model training, ensemble experimentation, deployment, and AI-generated clinical reporting.
I have also built AI-powered knowledge assistants and automation workflows that integrate platforms such as Notion, Jira, Supabase, WordPress, and social publishing tools. These projects strengthened my interest in building complete AI systems, not just isolated models.
Why AWS?
As AI applications move beyond prototypes, cloud infrastructure becomes essential. A useful model is only one part of a production system. It also needs secure data storage, scalable APIs, monitoring, deployment pipelines, access control, reliability, and cost management.
This is where I see AWS playing a major role in my journey.
My next goal is to move from understanding AWS services individually to designing reliable, production-ready architectures with them. I am particularly interested in learning more about Amazon SageMaker, Amazon Bedrock, containerized deployments, event-driven systems, model monitoring, and cost-efficient AI infrastructure.
What I Plan to Share
Through the AWS Builder Community, I intend to document what I learn while building practical AI and cloud projects. Some of the topics I hope to explore include:
- Deploying FastAPI-based AI applications on AWS
- Building secure Retrieval-Augmented Generation pipelines
- Comparing Amazon Bedrock with direct model API integrations
- Creating serverless AI workflows with Lambda
- Managing documents and model artifacts using S3
- Monitoring AI applications with CloudWatch
- Designing scalable architectures for AI agents
- Understanding the practical transition from AI prototype to production
- Exploring MLOps patterns for deployment, evaluation, and continuous improvement
I want my articles to be honest and implementation-focused. Along with successful approaches, I will share architectural decisions, limitations, mistakes, cost considerations, and lessons learned while building.
What I Hope to Learn
I am joining this community not only to publish but also to learn from engineers who have already solved difficult problems at scale.
I am especially interested in connecting with builders working in:
- Generative AI and LLM applications
- MLOps and model deployment
- Cloud and DevOps engineering
- Serverless architecture
- AI product development
- Enterprise knowledge systems
- Responsible and observable AI
My long-term goal is to grow at the intersection of product thinking, AI engineering, and cloud infrastructure. I believe this combination can help create AI products that are technically capable, operationally reliable, and genuinely useful to their users.
I’m excited to build, experiment, document the process, and contribute to the AWS Builder Community.
If you are also working on AI, MLOps, cloud architecture, or developer tools, I would be glad to connect and learn from your work.
Let’s build.
Enjoyed reading this content? Let the author know!
Your likes, comments, shares, and saves help creators reach more builders.
Loading recommendations
Loading article