Software Engineer vs AI
The survival guide
Volodymyr Vyshko, 2024
Agenda
Current state of AI
You are here
Companies reaction
Who can lose the job
AI for web devs
Quiz / gift
AI video generation 1 Year ago...
UI/UX Jobs
AI
AI
AI
AI
AI
How companies react
LLM
LLM
LLM
RAG
ML
LLM
Vector DB's
RAG
Prompts
Vocabulary
Tech interview process is changing
( risk of losing a job )
Requirements
Documentation
Code
Programming work inptut/output model
Review & Remarks
0
No discurrions with PO, no proactivity, no product thinking
Single (regular) specialization
Rutine work
Implement forms
Implement CRUDs
Validations
Boilerplate
do what BA says
Same bugs
Not using AI tools
Copilot
Prompt engineering
LLM
GPT
MLOps
RAG: Retrieval Augmented Generation
Azure OpenAI studio demo
1. Keep learning Computer Science
2. Work on soft skills
3. Develop T-shaped profile
4. Use AI tools
5. Try-out LLM APIs
import OpenAI from "openai";
const openai = new OpenAI();
async function main() {
const stream = await openai.chat.completions.create({
model: "gpt-4o-mini",
messages: [{ role: "user", content: "Say this is a test" }],
stream: true,
});
for await (const chunk of stream) {
process.stdout.write(chunk.choices[0]?.delta?.content || "");
}
}
main();
Open WebUI (Formerly Ollama WebUI)
curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey \
| sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg
curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list \
| sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' \
| sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
sudo apt-get update
# Configure Docker to use Nvidia driver
sudo apt-get install -y nvidia-container-toolkit # NVIDIA Container Toolkit
sudo nvidia-ctk runtime configure --runtime=docker
sudo systemctl restart docker
# Start the container
docker run -d --gpus=all -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama
# Add a UI to your Chat assistant
docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
"tabAutocompleteModel": {
"title": "Codellama",
"provider": "ollama",
"model": "codellama:7b-code-q5_K_M"
},Add a code assistant to your VSCode
OpenAI
Prompt eng.
LLM
Graph DB
AI tools
GH Copilot
T-shaped skills
Github account with demo projects
Show how the project become better
6. Work on resume
QUIZ
Join quiz!
Win a prize!
Thank You!
