Skip to main content

Using AI to Reinvent My Résumé and Try to Land an Interview



Creating a résumé is a tedious job to most. It's hard, time consuming and might even be the cause for rejection-if you don't know what you're doing. Fortunately, there are AI tools out there that created to assist, us humans, in generating résumé. It save's time, effort and you get higher chance of being hired. 

But what if you're transitioning to an entirely different role? You don't have experience, no educational background to back it up. and no portfolio to show. What do you do? You come up with something creative. You come up with some that has never been done before. And, just wow them... or at least try.

I was messaged in LinkedIn for a position that I was eyeing for in years. The HR guy reached out and we scheduled a call interview. We talked for more than half an hour and I was enlightened that my résumé is lack-luster. I was highly considered but the résumé is not at par because I have no job experience on AI, the certifications we're not included, and I don't have any portfolio to show. 

So I got creative.

I collaborated with ChatGPT in creating a project proposal fit for the position. If photographers use portfolio to showcase their shot and musicians use recordings to demo their song, it's only fitting in my opinion to generate a document such as a project proposal to exhibit my prowess in prompt engineering.

Everything's submitted. Now let's see what will happen.


Labels:

Popular

Conversations with Grok (Part 1): Introducing Agile Transportation System

Me: What do you think of agile Transportation System? Grok : It seems like you might be referring to "Agile Transportation System." Did you mean a specific system, like a company, a concept, or something else? I’ll assume you’re asking about agile transportation in a general sense—like how agility applies to transportation systems—and go from there. If I’ve got it wrong, just let me know! Agile transportation typically refers to a flexible, responsive approach to moving goods or people. Think of it as a system that can quickly adapt to changes—whether that’s shifting demand, unexpected delays, or new tech. In practice, it’s about efficiency and speed without sacrificing reliability. For example, logistics companies might use real-time data to reroute trucks around traffic, or cities could tweak public transit schedules based on passenger patterns. It’s all about staying nimble in a world where disruptions—like weather, supply chain hiccups, or even pandemics—can throw a wrenc...
Read more

recipe: pinesang itlog (souped egg)

i love to eat and cook. so, i always stay in the kitchen to get the first taste on any food cooked by my mom. eventually, i learned some of them. and here's one: pinesang itlog ingredients: 5 thick slices ginger 2 cloves garlic 1/2 bulb onion, diced 5 tablespoon fish sauce (patis) 1-3 eggs pechay/dahong sibuyas half liter water directions: suate garlic till brown. add onion and ginger. pour fish sauce and let sizzle. add water. let it boil for 5 minutes. add the vegetables. let it boil for 2 minutes. add eggs and let boil for few minutes till the eggs harden. serve and enjoy!
Read more

Retrieval-Augmented Generation (RAG) Using First-Principles Thinking

Instead of just learning how Retrieval-Augmented Generation (RAG) works, let's break it down using First-Principles Thinking (FPT) —understanding the fundamental problem it solves and how we can optimize it. Step 1: What Problem Does RAG Solve? Traditional AI Limitations (Before RAG) Large Language Models (LLMs) like GPT struggle with: ❌ Knowledge Cutoff → They can’t access new information after training. ❌ Fact Inaccuracy (Hallucination) → They generate plausible but false responses. ❌ Context Limits → They can only process a limited amount of information at a time. The RAG Solution Retrieval-Augmented Generation (RAG) improves LLMs by: ✅ Retrieving relevant information from external sources (e.g., databases, search engines). ✅ Feeding this retrieved data into the LLM before generating an answer. ✅ Reducing hallucinations and improving response accuracy. Core Idea: Instead of making the model remember everything, let it look up relevant knowledge when needed....
Read more