FEDEVEL
Platform forum

arda , 05-15-2026, 09:48 PM

Hello, I'm Arda from Türkiye. I enjoy following your content. I'm currently a third-year electrical engineering student and will graduate next year. I'd like to ask you a question about this. I want to develop my skills in Altium and advance my career in hardware design, and I'm working on projects in this area. However, AI worries me. As a young engineering student, I'm concerned that AI will take over the design sector and that I'll end up like software engineers before I can develop my skills in this career path. You share your opinions on AI, saying it's not ready yet. What can we say about the future? Is it possible for a new engineer to develop their skills and avoid unemployment? Thank you in advance for your answer.

, 05-15-2026, 09:53 PM

🤖 In the meantime, here’s a response from the [FEDEVEL AI HW Assistant]().
It helps to find relevant resources for your question, but it may make mistakes as it’s still in early development.

This is the response from the AI Assistant:
Here's my perspective based on current industry developments and insights from hardware design experts:

**AI in Hardware Design Today:**
1. **Assistive Tool, Not Replacement:** Current AI applications in PCB design (like automated routing suggestions or component selection) are productivity boosters rather than complete solutions. They help handle repetitive tasks but require human oversight for final decisions and complex problem-solving [Source 14](https://www.youtube.com/watch?v=aAB6qMQwykg&t=2909).

2. **Limited Understanding:** While AI can generate schematics and basic code, it struggles with system-level understanding, design intent, and real-world constraints like EMI/EMC considerations [Source 17](https://www.youtube.com/watch?v=gHC7uZBigmQ&t=994).

3. **Physical Implementation Challenges:** PCB layout requires understanding mechanical constraints, thermal management, and manufacturing realities - areas where human intuition and experience still dominate [Source 10](https://www.youtube.com/watch?v=bw4KxhV-d8g&t=5747).

**Future-Proofing Your Career:**
1. **Focus on Fundamentals:** Deep understanding of electronics theory, signal integrity, and manufacturing processes will always be valuable. AI tools need skilled operators who can validate and refine their outputs [Source 8](https://www.youtube.com/watch?v=I_MNw4EWer0&t=1906).

2. **Develop System Thinking:** Learn to manage entire product lifecycles - from concept to manufacturing.

, 05-15-2026, 09:53 PM

AI currently can't handle cross-disciplinary coordination between electrical, mechanical, and software teams [Source 5](https://www.youtube.com/watch?v=I_MNw4EWer0&t=6259).

3. **Embrace AI as a Tool:** Future engineers will need to work with AI systems, similar to how we use simulation tools today. Focus on developing skills in:
- Defining good constraints for AI tools
- Validating AI-generated designs
- Troubleshooting unexpected results [Source 13](https://www.youtube.com/watch?v=T2WXlEwhI8k&t=5520)

**Industry Perspective:**
Experienced designers predict AI will create new roles rather than eliminate existing ones. As one expert noted: "AI will handle routine layout tasks, freeing engineers to focus on architectural innovation and complex problem-solving" [Source 15](https://www.youtube.com/watch?v=T2WXlEwhI8k&t=5330).

**Action Steps:**
1. Build physical prototypes - hands-on debugging teaches irreplaceable skills
2. Study failure analysis - AI struggles with diagnosing unexpected behavior
3. Learn to document design decisions - critical for AI training and validation
4. Develop cross-domain knowledge (mechanical, RF, power) - makes you adaptable

The engineers at risk are those who only do repetitive layout work. Those who understand the "why" behind designs and can manage complex systems will thrive. As hardware becomes more complex, we'll need more skilled engineers - not fewer - to guide and validate AI tools.

You can continue chatting with the AI Assistant here:
https://fedevel.com/hw-assistant

Auki , 05-16-2026, 11:08 AM

AI will not take software developers’ jobs. Software developers who use AI effectively will take the jobs of those who don’t. The same will be true in the EEE field as well.

Robert Feranec , 05-18-2026, 07:24 AM

I think, right now it is hard to say what exactly is going to happen in the coming years. SW is easy for AI because it is pure text and current LLM AI systems are good at text. For HW, AI is more difficult - some schematics and boards can be specified in TEXT files, but text representation may not be good enough as HW may need to work more with geometries, rather than bare text. HW is also about measurement, debugging, probing, ... - that may be also possible to do with AI + some kind of robotic system, but not as easy as SW. Soon I will be publishing a video about Quilter, if you are interested about AI in HW, it may be interesting for you.

QDrives , 05-18-2026, 10:49 AM

As long as you think yourself and **not** blindly follow you should be safe.
There is a lot of incorrect data on the internet and AI assumes that if lots talk about then it must be correct.