Google GenAI Program — Skill Badges
A focused learning sprint across GenAI, cloud MLOps, data engineering, and AI infrastructure. I packaged the outcomes as a single program page to keep the Learning section scannable (badges as screenshots, links optional).
Learning Outcomes
- GenAI foundations: LLM basics, attention/encoder-decoder/transformers, and practical prompts for applied tasks.
- Vertex AI evaluation & MLOps: Model evaluation mindset, monitoring signals, and production workflows for GenAI systems.
- Cloud data engineering: End-to-end pipelines: ingestion → processing → serving, plus serverless patterns (e.g., Dataflow).
- Infrastructure for AI: How GPUs/TPUs and “AI hypercomputer” building blocks map to training/inference trade-offs.
- Platform engineering: Kubernetes foundations (GKE) and how to think about deployment and reliability in practice.
- Applied APIs: Using ML APIs to accelerate product prototyping when bespoke models are unnecessary.
Badges (Credential IDs)
Tip: if you prefer, we can add the public credential links later (kept optional to avoid an overly link-heavy page).
Takeaways
I completed a set of Google skill badges inside a GenAI learning program, covering four threads: (1) LLM fundamentals, (2) Vertex AI evaluation + GenAI MLOps, (3) cloud data engineering, and (4) AI infrastructure. Because there are many badges, I grouped them under one “program” page rather than listing each badge as a separate Learning card. For the portfolio, the screenshots are the quickest proof, and the credential IDs are there for reference. If needed, I can also attach the public credential links, but keeping links optional avoids turning the page into a long list of outbound URLs.