Careers, Roadmap & Your First GenAI App

Where can this course take you, and what will you build along the way? In this session we look at the main GenAI job roles, walk through the course roadmap, and then build and deploy your first GenAI app in about 30 lines of Python.

01Career paths and job roles

GenAI jobs have names that overlap, and companies use them differently. Here is what each role usually means:

02The course roadmap

The course moves from foundations to building real systems. Each module builds on the one before:

• Each session has diagrams, live demos, code you can copy and a 5-question quiz.
• Practice matters more than reading: run every code block yourself in Colab or on your laptop.
• Expect to be confused sometimes. Neural networks and attention take two or three reads; that is normal.
• Use the cheat sheets at the end of each module for revision.

03Hands-on: your first GenAI app

Let us build “Explain Like I’m 10”: type any topic, pick a level, and an LLM explains it. We use Streamlit, which turns a Python script into a web page (Session 3 covers it in more detail).

# app.py: a tiny GenAI app.  Run:  streamlit run app.py
import os
import streamlit as st
from openai import OpenAI

st.set_page_config(page_title="Explain Like I'm 10", page_icon="💡")
st.title("💡 Explain Like I'm 10")

def get_key():
    if os.getenv("OPENAI_API_KEY"):              # local: from your .env / environment
        return os.getenv("OPENAI_API_KEY")
    try:
        return st.secrets["OPENAI_API_KEY"]      # cloud: from Streamlit secrets
    except Exception:
        return ""

api_key = get_key()
if not api_key:
    st.warning("Add OPENAI_API_KEY to your environment or to Streamlit secrets.")
    st.stop()
client = OpenAI(api_key=api_key)

topic = st.text_input("What should I explain?", placeholder="e.g. How does UPI work?")
level = st.select_slider("Level", ["Child", "Student", "Professional"], value="Student")

if st.button("Explain") and topic:
    with st.spinner("Thinking..."):
        reply = client.chat.completions.create(
            model="gpt-4o-mini",
            temperature=0.3,
            messages=[
                {"role": "system", "content": f"Explain topics simply for a {level.lower()}. Max 120 words."},
                {"role": "user", "content": topic},
            ],
        )
    st.write(reply.choices[0].message.content)

Install and run it:

pip install streamlit openai
export OPENAI_API_KEY="sk-..."      # Windows PowerShell:  $env:OPENAI_API_KEY="sk-..."
streamlit run app.py

• st.text_input and st.select_slider create the input boxes.
• The system message tells the model how to behave; the user message is the topic.
• temperature=0.3 keeps answers focused (Session 24 explains why).
• If no key is found, the app shows a warning and stops instead of crashing.

04Deploying to the cloud

An app on your laptop helps only you. Let us put it online, for free, with Streamlit Community Cloud:

05Summary

• Main roles: GenAI Engineer, LLM Engineer, AI Product Engineer, LLMOps Engineer.
• The course goes foundations → transformers → building real apps.
• A GenAI app can be ~30 lines: Streamlit UI + one LLM API call.
• Deploy from GitHub to Streamlit Community Cloud and keep the key in Secrets, never in code.

06Quick quiz

07References

• Streamlit documentation
• Deploy on Streamlit Community Cloud
• OpenAI API quickstart