Edward Praveen

Senior ML Engineer & AI Architect. Building production-grade LLM systems on AWS.

Hello! I’m Edward Praveen.

About Me

I’m a Senior Machine Learning Engineer and AI Architect focused on building production-grade AI systems that solve real-world problems.

My work centers around designing and deploying scalable machine learning and LLM-based applications, with a strong emphasis on reliability, performance, and practical usability in enterprise environments.

What I Do

I specialize in end-to-end AI system development - from model experimentation to production deployment. My core areas include:

  • Large Language Models (LLMs) and multi-agent systems
  • Retrieval-Augmented Generation (RAG) and Text2SQL systems
  • MLOps pipelines and model lifecycle management
  • Fine-tuning techniques such as LoRA and QLoRA
  • Scalable cloud architectures on AWS

Tech Stack

I work extensively with modern cloud-native and AI tooling, including:

  • AWS (Bedrock, EKS, SageMaker, OpenSearch, RDS, AgentCore)
  • Kubernetes, Docker, Helm, ArgoCD
  • Python-based backend systems and API design
  • Observability, monitoring, and performance optimization

What I Focus On

I’m particularly interested in bridging the gap between AI experimentation and production systems - ensuring models are not just accurate, but also scalable, secure, and maintainable.

My work often involves:

  • Designing multi-agent workflows for complex reasoning tasks
  • Optimizing inference and system performance
  • Building data-driven applications that generate actionable insights

About This Blog

This blog is a collection of hands-on tutorials, architecture deep-dives, and production engineering insights - published weekly.

You’ll find:

  • End-to-end tutorials covering AI/ML engineering, cloud infrastructure, and DevOps
  • Architecture patterns from real client engagements, explained with synthetic data and working code
  • System design decisions - the trade-offs considered, the options rejected, and why
  • Production lessons from deploying LLM systems at scale on AWS

If you’re building AI systems, designing cloud infrastructure, or navigating the gap between ML research and production engineering - this is for you.