About
Raj Murugan
Senior AWS Solutions Architect at Parallo (SoftwareOne, AWS Advanced Partner). I take customers from "we want AWS" or "we want GenAI" to a working, governed deployment, then write about how it actually works and where it breaks.
Sydney · 12 posts · AWS Solutions Architect Professional · AWS Certified AI Practitioner
Work with me
Most of my engagements are AWS migrations, GenAI builds on Bedrock and AgentCore, or presales architecture under AWS funding programmes (MAP, MMP, AppMod, GenAIIC). Regulated industries are where I'm most useful: pharma and GxP, healthcare, radiotherapy SaaS, iGaming. If something in the writing here sounds like the problem you're trying to solve, the fastest way in is a 15-minute call.
Book a 15-minute callBackground
Around 20 years in IT, more than ten of those focused on AWS. Three lanes: presales architecture, customer delivery, and hands-on AI and cloud engineering. The day job at Parallo is shipping production AI agents on AWS for enterprise clients. The nights and weekends are spent building the same kinds of systems for my own problems and writing up what I learned.
The work I publish here is the work nobody else writes about: the IAM trust policy that takes an afternoon to debug, the VPC cold start that breaks streaming, the OIDC flow that silently fails for a month. AgentCore production gotchas. CDK patterns that survive a real deployment. Cost decisions that show up on the bill, not in the demo.
If you're shipping agentic AI on AWS and you've started hitting walls the documentation doesn't mention, this blog is for you.
How I write
Evidence-led. Claims back up with numbers, mechanisms, or a worked example. I name flaws in my own posts rather than ship a clean-looking-but-wrong narrative. The wins I publish come from real engagements, sanitised to anonymise the customer.
Where I publish
Certifications
In progress: AWS Certified Generative AI Developer Professional
Stack
Focus areas
- Bedrock in production: latency, cost attribution, agent call patterns
- AgentCore and Strands hands-on builds and gotchas
- Observability for LLM apps (ADOT, OTEL, session-end detection)
- Regulated-industry delivery (GxP, healthcare, iGaming)
- AWS funding pathways (MAP, MMP, AppMod, GenAIIC)