Why now?
Over the past year, I've had the chance to build and experiment with several AI-based applications through hackathons, side projects and other hands-on exploration.
That work gave me practical exposure to a lot of exciting subtopics such as: semantic/hybrid search, retrieval (RAG) workflows, LLM-powered applications and different real-world use cases for AI systems. I learned a lot by building and honestly, that has always been one of my favorite ways to learn. For me, knowledge expansion has always been a pipeline of Learn -> Build -> Refine -> Encounter problems -> Repeat.
Now I'd like to formalize and combine this AI knowledge with my existing AWS cloud experience and that's why I'm starting my AWS Generative AI Developer Professional certification journey.
Background
My background is in cloud, software, and systems/solution architecture, while my recent work has pulled me further into the AI side of things. This certification feels like it'd help me bridge Cloud and AI worlds.
What do I hope to gain?
- A more structured understanding of generative AI specifically on AWS. I'd been leveraging different stacks which are not AWS-based. For example my prompts are stored as either string templates in codebases or builder-pattern classes, as opposed to a cloud-based prompt management tool with versioning such as AWS Bedrock Prompt Management. My vector database is typically either pinecone, chromadb or postgres/pgvector hosted locally or on Supabase.
- Stronger fundamentals around designing and deploying production-minded AI systems.
- A clearer view of best practices, tradeoffs and filling in AI architecture pattern gaps.
- Turn my scattered self-taught AI experience into something more deliberate and focused
What else?
I'm hoping to use this as an opportunity to write more openly about what I'm learning. In the past, I'd learn in the dark and would have regrets about not documenting my thoughts in more detail. I want to document my progress, epiphanies, and struggles so I'm starting out this journey with this post as the start of a small #devjournal series to do that.
I'll write about what I study, what stands out, what surprises me and where I find gaps between theory and practice. Hopefully, this will help me reflect more clearly about what I learn and also be useful to others who are trying to bridge cloud engineering/development and modern AI development.
Top comments (0)