A few days ago, I came across a job posting from Commonwealth Bank that resonated with me on every level.
The position — Software Engineer in their Business Banking Gen AI team — wasn’t just another developer role. It was exactly aligned with how I’ve been learning, building, and thinking about software development over the past year. It highlighted tools I use daily (like Cursor and Gemini), frameworks I’m eager to master (like LangChain and AutoGen), and most importantly, a mindset I strongly believe in:
“The future is not about avoiding AI — it’s about mastering how to work with it.”
Why This Job Matters to Me
The job post emphasized:
- Using AI-assisted tools and coding workflows
- Building Retrieval-Augmented Generation (RAG) pipelines with frameworks like LangChain and LlamaIndex
- Experimenting with agentic AI systems like AutoGen and SemanticKernel
- Collaborating in teams where AI is not just a tool, but a co-pilot
As someone who has been building and deploying AI-powered web services using tools like ChatGPT, Gemini, and even custom-trained machine learning models, I felt like this role was written for someone exactly like me.
How I’ve Been Preparing for This Era
Over the past year, I’ve:
- Built and shipped no-code/low-code AI tools using Cursor, ChatGPT, and MCP
- Created services that leverage Gemini and OpenAI APIs via advanced prompt engineering
- Trained a custom machine learning model to diagnose plant diseases and deployed it as a real-time web service
- Deployed scalable, AI-enhanced platforms like Before You Go and Part-Time Mate
But I now realize that to reach the next level — and be truly aligned with the GenAI direction companies like CommBank are taking — I need to go deeper into:
- Retrieval-Augmented Generation (RAG) systems
- Multi-agent orchestration with frameworks like AutoGen
- AI-first software architecture that blends LLMs, vector databases, and modern frontends
My Vision as a Developer
I believe we’re entering a new era of development — one where developers won’t just write code, but design intelligent workflows with AI as a core collaborator.
This blog is where I’ll document that journey.
I’ll learn and break down frameworks like LangChain, Weaviate, and AutoGen.
I’ll build GenAI projects and share both successes and failures.
And most importantly, I’ll record how AI is not replacing us — but elevating those who know how to work with it.
What’s Next
My first hands-on project will be building a RAG chatbot using LangChain, OpenAI, and FAISS — trained on my own portfolio and documents.
In the coming posts, I’ll break down:
- What RAG is and why it matters
- How I implemented it step by step
- And how it connects to the AI-first career I’m pursuing
Stay tuned.
[요약 – 영어 원문 해설]
최근 커먼웰스 뱅크(Commonwealth Bank)의 AI 소프트웨어 엔지니어 채용 공고를 보고 큰 영감을 받았습니다. 제가 평소에 사용하던 도구들(예: Cursor, Gemini), 그리고 제가 만들고 배포해온 AI 프로젝트들과 너무 정확히 맞아떨어졌기 때문입니다.
이 글에서는 다음과 같은 내용을 다루고 있습니다:
- 앞으로 개발자의 시대는 AI를 배제하는 것이 아니라, 얼마나 잘 활용하느냐의 경쟁이라고 생각합니다.
- 저는 이미 AI API, 프롬프트 엔지니어링, 머신러닝 모델 등을 활용한 다양한 프로젝트를 해왔고, 이제는 LangChain, AutoGen 같은 GenAI 프레임워크들을 본격적으로 익히고 있습니다.
- 앞으로 이 블로그를 통해 제가 배우는 과정, 실습 결과, 느낀 점을 기록해나갈 예정입니다.
요약하자면, 이 글은 “AI를 잘 다루는 개발자”로 성장해 나가는 여정의 첫 글입니다. 영어가 익숙하지 않더라도 글의 핵심 메시지는 “AI를 어떻게 활용할 수 있을까?“에 대한 고민과 실행이라고 보시면 됩니다.
'AI Study' 카테고리의 다른 글
| Step 2: Expanding RAG – Multi-Document Chatbot with PDF Support (0) | 2025.06.04 |
|---|---|
| What is RAG? Building my first LangChain-based document chatbot (0) | 2025.06.02 |
| 프로그래밍 수학 - 확률과 선형대수, 어디에 쓰일까? (0) | 2025.03.30 |
| 알고리즘과 수열, 그리고 파이썬과 인공지능의 연결 (0) | 2025.03.26 |
| 인공지능을 위한 프로그래밍 수학 (0) | 2025.03.23 |