쉐도잉 연습: Fastest way to become an AI Engineer in 2026 - 영상으로 영어 말하기 배우기

you're looking to become an AI engineer

if this job is on your radar then this video is

all you need it's a full breakdown of what this role is how it differs from software engineering

and machine learning engineering and how to become one

so I'm going to give you a full roadmap what projects

you should be doing what kind of person this job would suit

and also my opinion on where see this role going

and is it worth your time to invest in okay before

we go any further i got into tech in my 30s i learned from scratch all this stuff

and i watched loads of videos like this i'm not just

going to give you a random roadmap you can get off chat gbt

when i was learning i wish someone taught me this stuff

but also said you can go out there whilst you're learning

and build your own products and sell them out there in the world

so you can learn to become an ai engineer and you can also make a SaaS.

Make something, sell it.

Worst case scenario, it looks good at an interview.

Best case scenario, it becomes a business.

So I'm here, my page, everything on my content is all about encouraging you guys to learn technology, but also believe in yourself,

sell your own stuff and see where it goes.

Because taking a chance might lead somewhere.

So this video is going to be four steps.

Each step is going to gradually increment.

At the end of it, I'm going to encourage you to make your own micro SaaS.

And if you're new here, my name is Andrew.

I'm a senior software engineer and I got into tech in my 30s totally from scratch

and I have worked in the AI space as an engineer.

So I've watched this role evolve over the last few years.

I make tech content around your career, around building apps.

So if that sounds like your kind of vibe, subscribe if you want.

Okay, before we go though, I want to just manage expectations because firstly, I want to give you correct factual information on this channel.

The chances of you getting your first role working for OpenAI

are very very low unless you look at further education so getting a master's or a PhD.

There are a lot of jobs below that there are

so many opportunities in AI below that so that should be your focus.

So clearly the reason this is taking off

and the reason the salaries are so high is that companies

and the world is crying out for people who can implement AI.

Okay firstly though, what is an AI engineer?

This is someone who builds production-ready systems using pre-trained AI models and APIs.

And to further set the scene here, let's talk about three roles.

So there's a software engineer, there's an AI engineer, and there's a machine learning engineer.

People confuse these last two a lot.

So a software engineer will write code or get AI to write the code nowadays, and that will produce a program.

Machine learning engineers, they take loads of data, they clean the data they fine-tune the model to create a program

or a model that will achieve some output the AI engineer makes

that model useful in the real world

so they'll make it into a real system or a real app okay

so this is not a machine learning engineer this is not

a machine learning researcher these are people deep in math people

who write research papers they train the models themselves this is not

that this is more like the practical use of AI so it's what comes after.

If it's still not quite clear, there's a really good article called the Rise of the AI Engineer, where they basically say that in the future, there's going to be more AI engineers than ML engineers.

There's a really good visual and it shows the line of an API.

On the left side, you've got the data, the research, the data science side.

On the right side, this is where the AI engineer comes in.

So this is the product and user focus.

You've got full stack engineers there so it's all about chains agents and making things basically.

With that said let's get into the roadmap.

So I've broken it down into four steps and how you learn this stuff you learn by doing.

You don't learn by watching tutorials or reading documentation you learn by becoming a problem solver.

So it's going to be four steps at the end of each step there'll be a project

so this is all project-based learning.

Step one is to focus on the core skills of AI engineering.

So Python, LLMs, and system thinking.

And to start with, everyone starts with Python.

This is the language of choice for AI and machine learning.

The community has chosen it.

You have R as well, but you have a lot of things built on top of Python, a lot of the libraries which just make it easier.

For example, PyTorch.

And if you've never coded or you've never learned a programming language before, these are some things which help me.

And the good mindset is that you're going to be learning Python for the rest of your career probably.

It's not something you're learning like a year.

It's just a continuous process.

But the real thing you're learning is problem solving.

And this is hard to teach.

What helped me was doing toy problems.

So there's a site called Code Wars.

It's totally free.

Start right at the beginning.

And whenever you're learning, try and start every session by solving one of these small problems in Python.

Also, only watch one video tutorial on Python and then build and use documentation.

So if you go courses, you could do YouTube courses.

Those are free Code Camp ones.

There's a BroCode one.

If you want a paid one and the one I learned from, it's zero to mastery.

They've got a really good structure, really good projects, and that's how I learned Python myself.

But the mindset is becoming a problem solver, so you want to get uncomfortable and learn all the basics of Python.

And also Git and GitHub.

So what you want to do is these projects I suggest, you want to be committing them to Git.

So you don't have to know everything about Git, it's just the main things like pushing, pulling, and merging.

There's a site called Learn Git Branching, which is quite good.

There's a few YouTube tutorials you can watch, and also a more advanced book called ProGit.

So these are all free resources.

But again, Git's the kind of thing.

Learn it early on because you want to be committing all your stuff because this is the workflow that real engineers use.

So learn Git as soon as you can.

Okay, next we're actually getting into the real AI engineering.

So we're going to call and go through OpenAI's API documentation.

100

There's loads there.

101

They're the biggest provider.

102

So it's a good start for you.

103

This is like one of the key parts of being an engineer.

104

So calling APIs, doing auth, requests, how to handle data, what data you get back.

105

There's actually a fair amount involved with like gluing APIs.

106

And it's something that took me a while to get to grips with.

107

So yeah, OpenAI is a great start.

108

They've got loads of documentation.

109

So get stuck in with the Python part.

110

Okay, the next part of the fundamentals is learning about the LLM basics and prompt engineering.

111

So this is something

112

that all software engineers are having to learn right now basically

113

how to use an LLM how to use AI effectively so the context window, temperature, tokens, input and output patterns,

114

learning all this stuff you'll need it in this role.

115

Thank you to Datacamp for sponsoring this part of the video.

116

Now I've said this loads of times but I taught myself the code

117

and got into tech at 30

118

and investing in my learning of some of these tech skills

119

was without doubt the best return on investment of my whole life.

120

And if you are serious about about becoming an AI engineer this year.

121

The fastest path is not just binge watching tutorials, it's building real systems.

122

This is why I recommend DataCamp, because it's really hands-on.

123

They've got short lessons, in-browser coding, guiding projects, and instant feedback.

124

And for most of you watching, you wanna look at this one here.

125

It is the Associate AI Engineer for Developers track.

126

Why?

127

Because it uses the exact stack that you'll use to ship AI features, like the OpenAI API, Hugging Face,

128

Langchain, Pinecone, Prompt Engineering, Embeddings, and LLM ops.

129

So you're learning how to build chatbots, semantic search and production ready AI apps, not just playing with prompts.

130

And if you're coming from a data background, then Datacamp also has this, the Associate AI Engineer for Data Scientist track.

131

And this one's interesting because it goes deeper into PyTorch, fine tuning models like Lama 3, MLOps and deployment.

132

And what's really cool is that these tracks prepare you for industry recognized Datacamp AI Engineer certifications.

133

So basically you get in the best of both worlds, practical experience but also a pathway to earning these industry recognized certifications in one place.

134

So if you want one structured, practical roadmap instead of just guessing what to learn next, check out Datacamp using the link in the description.

135

And wherever you're starting from there will be a track for you and if you do check it out, hope you enjoy it.

136

Alright, the last part of the fundamentals is to start thinking in terms of systems.

137

What do I mean by this?

138

So think of a small AI workflow and just kind of sketch it out

139

so you have an idea of how all the pieces fit

140

together in terms of like a big picture bird's eye view or like a tiny agent framework.

141

So just sketch it out just so you have an understanding of the big picture.

142

This will really help you going forwards.

143

For the final step I mentioned we're going to do a project

144

which is going to bring everything together that you've learned

145

and it's going to be a personal research assistant CLI using Python and also calling the OpenAI API.

146

So basically you'll ask it questions and it will structure the answers but also you can ask follow-up questions.

147

So this is a nice project you can use git you can use python you're gonna call the openai api

148

and put it all together that you've learned quick pause

149

if you're enjoying this content

150

if you're getting any value from it it's totally free for you i would massively appreciate it

151

if you like the video and subscribe

152

if you want it would help me out massively motivates me

153

to make more videos like this to encourage you guys to build to learn

154

and to use technology to change your life as it has done for me.

155

Back to the video.

156

Okay, step two.

157

Now we're getting into the nitty-gritty, the real stuff.

158

So back-end, architecture, and rag.

159

So we're going to learn how to build real back-ends with FastAPI and Pedantic.

160

So if you're a software engineer now, maybe you know this already and you can just add on these new technologies.

161

Or if you're a computer science student, maybe you use Java, whatever, then just shifting, learning back-end, but learning Pedantic and FastAPI.

162

And particularly things like async endpoints,

163

background jobs, dockerize services, kind of key fundamental parts of backend working as an AI engineer.

164

We're going to pick up Postgres.

165

So Postgres, really popular.

166

I learned it a couple of years ago.

167

There's loads of resources on YouTube.

168

You won't struggle to find resources for free on this.

169

We're going to look at queues, migrations, event-driven patterns, and just get into grips with the database technology.

170

You can actually build a decent amount of stuff with just step one.

171

But step two is all about real backend services.

172

So not local, all right?

173

Because when you go into a real job, they're going to be using a lot of different things in the environment.

174

They're going to have a database.

175

They're going to use Docker probably.

176

And obviously, backend, like FastAPI.

177

So getting really deep into this.

178

And I spend a lot of time in this area.

179

And after Postgres, at this point in step two, we're going to learn RAG.

180

Learn RAG end-to-end.

181

Fundamental concept.

182

Going to be using it a lot.

183

So embeddings, vector databases, chunking, all this kind of stuff.

184

There's a really good two hour, I think, free CodeCamp tutorial, completely free, I used a year or two ago.

185

It's really good.

186

And the whole goal of section two is to design

187

and implement an AI backend using FastAPI that talks to a database using Postgres and has custom data sources.

188

So the project, so every step will have a project.

189

For this one, it's going to be a docs Q&A backend.

190

So we use a fast API service where you can basically upload PDFs and markdown notes.

191

Then we'll chunk, embed, and store in a vector database.

192

So that will use Docker, which again, you can use free CodeCamp to learn.

193

It's one of the most used technologies in tech.

194

You will not struggle to learn it.

195

And also a Postgres database.

196

Okay, next, we're on to step three.

197

And we're getting deep into this learning actual real skills, which are valuable in production-ready AI systems like monitoring, evals, and safety.

198

Because AI systems can be tricky.

199

This is not just step-by-step programming.

200

They can hallucinate.

201

They can just add in randomness.

202

So we need a way to measure the cost, the efficiency, and reliability of our AI systems.

203

So this is what we're doing now.

204

Okay, first we add in observability and tracing.

205

And there's a tool called Langtuse for this.

206

It's open source.

207

And what that will do is that every LM call we make, It will log the inputs, outputs, the latency, and the cost.

208

So we can evaluate as we go on.

209

We can see how effective it is and try and reduce that randomness in those hallucinations.

210

Next is the safety element.

211

So we add in guardrails.

212

For example, prompt injection defenses so hackers can't trick a bot.

213

Or filters to catch and redact personal information.

214

Output validation to make sure responses follow our format.

215

And also safety rules to block harmful content.

216

So there's a tool called Sentry as well, which can catch those runtime crashes.

217

And this is key because this is what differentiates real AI engineers who work with production ready apps.

218

So if you can talk about this in an interview, the goal is to measure the quality of our system with numbers

219

so we can catch regressions before a user would notice and just keep the whole system reliable and safe.

220

Okay, and the project for step three, we're just going to take what we made in step two, the docs Q&A and just make it production ready, add in what we've learned in this step.

221

So we're going to layer on lang fuse tracing

222

so we can see every lm call we're going to add in the test data set

223

so just add in like 50 or

224

so real questions we're going to hook up lm as judge scoring

225

so gpt4 will automatically just grade the responses add in the stuff we learned

226

so prompt injection filters redacting personal data and add in sentry as well

227

so we can just catch any crashes we get and bum

228

that is a production ready app and that will look quite good at interview

229

okay step four is deployment so getting this real production ready ai system

230

that we've built and getting out there in the wild

231

and there's a lot to this it's cicd

232

which you you're gonna have to learn it's cloud it's just all the little things involved with making something locally

233

and then shipping it getting out there in the world making

234

it reliable making it the infrastructure good let's get into the steps

235

and how we do this is first you want to pick a cloud provider

236

so i recommend aws you can also do Azure, learn about the platforms, whichever one you choose.

237

This is going to be a key part of the role.

238

Obviously, if you're a backend developer, you probably know about this already.

239

Then get your Dockerized backend running there with proper HTTPS, environmental variables, and also logging setup.

240

Next, you want to get into CICD.

241

Most companies, most web apps nowadays are set up with this kind of pipeline, unless they're really backwards, and it will automatically deploy without you having to do anything.

242

So you can also add in monitoring, health check endpoints, alerts when things break, and also just to keep an eye on costs.

243

And the goal with this step overall is to show an employer, an interview that you can independently build,

244

deploy, and run a production-grade AI application without needing your hand-holding.

245

So the way you do this is just ship a few of them.

246

I recommend three.

247

And yeah, get this out there.

248

Put it in a GitHub repo.

249

Put it out there for people to see showcase yourself show of everything you've learned

250

so lms apis rag you know a good clean back-end structure

251

with monitoring it's all about showing yourself off showing good code

252

and applying for jobs okay to finish we're gonna make the last project on step four

253

and we're gonna bring it all together and i think

254

if you can go to an interview

255

and show off this project it looks pretty cool

256

so it's gonna be a production ready ai micro sass what

257

we're going to do is take the docs QA bot we made, add on a simple web UI so people can see it in a browser

258

so just use something like Gemini which is good for front ends.

259

That's good because it'll teach you more about front end as well.

260

We're going to add in user authentication so it's not wide open, a pricing gate with a free tier but also paid API limits too.

261

Then deploy it all with CICD which we learned earlier with health checks, some basic metric dashboard, a public landing page as well documentation

262

so you can go to an interview and this is a real product

263

but also you can maybe even charge for yourself so

264

when you're making this think of something that you actually want to build something

265

which has like a production ai micro sass and just try

266

and build it okay and that's the steps

267

so now you're in the position where you can apply for an ai engineer role

268

but also you can actually build your own ai micro sass

269

so hopefully this video helped i didn't want to make a random video of a roadmap chat gpt can provide

270

that for you but if you go through these steps

271

and appreciate that this is not just like you don't learn python

272

and then move on you're constantly learning these things and

273

if you keep improving someone will take a chance on you

274

you might have to be pragmatic with your first job i

275

was i started off as a wordpress developer then was a software engineer in an ai startup

276

so hope that helps

277

if you got value from this video only thing i ask i appreciate it

278

if you like the video and subscribe if you want happy coding i'll see you in the next one ciao

📺 같은 채널

Don't choose the wrong tech career in 2026

University StudentsBusiness English+1

How I Would Learn Python FAST (if I could start over)

Working Adults

✨ 추천 영상

70 문장

쉐도잉이란? 영어 실력을 빠르게 키우는 과학적 방법

쉐도잉(Shadowing)은 원래 전문 통역사 훈련을 위해 개발된 언어 학습 기법으로, 다언어 학자인 Dr. Alexander Arguelles에 의해 대중화된 방법입니다. 핵심 원리는 간단하지만 매우 강력합니다: 원어민의 영어를 들으면서 1~2초의 짧은 지연으로 즉시 소리 내어 따라 말하는 것——마치 '그림자(shadow)'처럼 화자를 따라가는 것입니다. 문법 공부나 수동적인 청취와 달리, 쉐도잉은 뇌와 입 근육이 동시에 실시간으로 영어를 처리하고 재현하도록 훈련합니다. 연구에 따르면 이 방법은 발음 정확도, 억양, 리듬, 연음, 청취력, 말하기 유창성을 크게 향상시킵니다. IELTS 스피킹 준비와 자연스러운 영어 소통을 원하는 분들에게 특히 효과적입니다.

섀도잉 방법: 단계별 전체 가이드 읽기 →

쉐도잉 연습: Fastest way to become an AI Engineer in 2026 - 영상으로 영어 말하기 배우기

Don't choose the wrong tech career in 2026

How I Would Learn Python FAST (if I could start over)

A Practical Guide To Becoming An AI Engineer (2026)

I cloned 3 apps and now make $35K/month

Tell Me About Yourself (The BEST Way to Answer this Interview Question)

How I Would Start Cybersecurity in 2026 (If Starting From Zero)

How To Land Your First Junior Dev Role

How to Become a Sales Engineer | Without Any Experience

If you’re an aspiring product designer, watch this (roadmap included)

SOFTWARE ENGINEER Interview Questions & TOP SCORING ANSWERS!

I'm an ex-Google interviewer. You're doing LeetCode wrong.

How AI Is Ruining Job Interviews

8 Years of Data Analytics Advice in 12 Minutes

The Art Of Winning In Tech

이 레슨에 대해

쉐도잉이란? 영어 실력을 빠르게 키우는 과학적 방법