JJ Asghar
Developer Advocate for the IBM cloud
Austin, Texas, United States
JJ works as a Developer Advocate representing IBM all over the world. He mainly focuses on the IBM Kubernetes Service and OpenShift, trying to make companies and users have a successful onboarding to the Cloud Native ecosystem. He’s also been known in the DevOps tooling ecosystem and generalized Linux communities. If he isn’t building automation to make his work streamlined he’s building the groundwork to do just that.
He lives and grew up in Austin, Texas. A father and husband, trying to learn to balance his natural nerdiness with family life. He enjoys a good strong dark ale, hoppy IPA, some team-building Artemis, and epic Gloomhaven campaigning.
He has recently dove headfirst into Fedora since IBM bought Redhat, but still secretly wants FreeBSD everywhere. He’s always trying to become a better web technology developer, though he normally just uses bash to get the job done.
Links
Awards
Area of Expertise
Topics
Using a Retrieval Augmentation Generation (RAG) AI system, built on stage and why you should use it
Stepping into the AI space, you quickly realize that there are many things that AI can do and many more things AI cannot do. There are some real challenges with grasping AI and what is realistic now. People assume there is a world of knowledge behind them when they interface with mainstream AI systems. This is true, but _most_ of this data isn’t tailored to your or your company’s needs.
In this talk, I’ll show you how to build a Retrieval Augmentation Generation (or RAG) based AI system easily, quickly, and securely. I’ll start with what you need to know about AI to grasp this, then build a simple one leveraging OpenAI and the nice portions of it, but understand the risks involved, then pivot to the free open source ecosystem, and then combine the security and simplicity of watsonx at the end.
Prompt Engineering
We will spend this time working through a workshop that will reinforce the introductory lecture and teach what you need to know to build out a successful prompt. With Part 2 of the lab (time permitting) we will tie the customized prompts to your watsonx assistant lab where you will actually see a full workflow leveraging watsonx at the core.
Leveraging Generative AI
Engaging in the AI ecosystem can be a daunting task. There are multiple options to start engaging, but no one gives you a clear path to some level of success. There are stories of advanced math or massive computing required; there must be an easier way. Or in another way to describe it, we don’t need to develop Microsoft Word, but it’s essential to know how to use Microsoft Word.
In this talk, I’ll be walking through an Open Source project called Caikit which is an Open Source wrapper around multiple AI portions of the ecosystem, so you can see the flexibility that it can give you. We will start with a simple whistle-stop tour of how to understand the AI space and then how to access public Open Source models. Then we will move over to my laptop live demoing Caikit via local containers and cached models to show how easy it is to play with it locally. From there, we will take the demo to the cloud and show a way to deploy it to OpenShift and be able to have an API that can respond with said model(s).
Walking out of this room, you’ll see how easy it can be with Open Source software; with a little effort on your computer and downloading some Open Source models, you can start leveraging AI with confidence.
Enterprise AI and Open Source
I grew up engaging in the open-source ecosystem. I have the advantage of being at IBM, where we build the Enterprise ready AI platform watsonx. With the way our industry is going we need some level of guard rails around the data and models that people are using and building, and IBM is trying to help build that.
Coming to this event series will allow me to speak as someone with decades-long exposure and influence from the open source community while learning to balance the Enterprise ready AI platform creating a unique and engaging viewpoint. We all need to understand how our future will pan out with what’s going on in the AI space, and if we don’t all agree on _how_ to make this successful, we will move to the dystopian futures that our movies predict.
Lessons Learned from Cultivating Open Source Projects and Communities
Over the last decade, I’ve had the privilege professionally of building and cultivating some Open Source projects and communities. To start off this isn’t a tools talk, this is a talk about the soft skills you have to have to be able to succeed as a leader in an Open Source project. My journey started tending the frequently asked questions for a small Linux Distribution called CRUX, and then years later professionally moved to the OpenStack-Chef project to build OpenStack clouds. I’ve grown other projects along the way, helped build tooling and communities, some successful and still running today, others were just flashes in the pan. I’ve learned a ton on this journey; honestly still am, but I have some lessons that are hard-learned and hopefully I warn pitfalls that can cause wasted cycles and pain. I’ll be going over:
Outline
This isn’t a tools talk
Scoping your project
Personally-backed
Corporate-backed
Empathy and audience is important
Celebrations
Defeats
Successful traits of Open Source projects
Trust
Clear Vision
Have a plan to move on if needed
Honestly, is it even worth this hassle?
We accidentally created a Serverless Application
As a developer advocate, one of the largest challenges we have is teach people how to use our products. To do this is that we have to create workshops and disposable environments so our students can get their hands dirty. As IBM employees we use the IBM cloud, but it is designed for long-term production usage, not the ephemeral infrastructures that a workshop would require. We have previously created some systems around it to provide different ways of building up these systems, but in this latest iteration, we discovered we created a full serverless stack (by accident).
Outline
Introduction
Our problem
Our iterations
Where serverless came into play
Our code
Where we can go from here
Was it worth it?
Introduction to Leveraging AI for Your Enterprise
With the emerging AI space, for enterprises, you need to know many terms and concepts before venturing into it. In this session, we will start with the foundational terms and experiences you must have to find the positives to leverage WatsonX to win in business. We will also demo some straightforward but valuable examples to help anchor your understanding. Our goal for this talk is for you to walk out of the room with the language (funny, eh?) and understand the typical workflow to start finding places to leverage WatsonX in your enterprise. The first step on this journey is to know the ecosystem and tooling; from there, you can find things to fit your business and get you on the road to success.
## Outline
- Introductions
- What do you need to know to start
- Let’s talk AI
- Consumer
- Business
- Let’s talk AI terms
- Model
- Training
- Types of Models
- sentiment
- summarization
- text generation
- image classification
- How can Enterprises can make this work
- Positives
- Negatives
- Demo
- Sentiment
- Summarization
- Image Classification
- cached
- downloaded
- Conclusions
Migrating a monolith to Cloud-Native and the stumbling blocks that you don’t know about
So your company has finally decided to move to the Cloud Native ecosystem. You’ve landed on containerization as your first step. You heard that all you needed to do was containerize your first app and then push it to Kubernetes/OpenShift/Nomad, and the cost savings just come. You’ve done this, and well, things have gone not as planned. Some of the tech didn’t do what you expected, and wait, what do you mean our OpEx has gone up?
Simply said: the promise of containerization or migrating to the Cloud Native ecosystem can be a lie if you don’t do your homework. Sadly most companies don’t. In this talk, I’ll explain a few gotchas that a “few” enterprises, in the guise of AsgharLabs, hit moving towards the Cloud Native world, and hopefully, you’ll learn from their mistakes, so you’re trip down this path will be more comfortable and closer to the promise.
Outline
Introductions
What is AsgharLabs and where they started, what they thought they needed to do
Where I came into the conversation to help AsgharLabs
Questions you should ask after getting your app containerized
Where are the architectural advantages and disadvantages?
Are we doubling up on things?
Isn’t automation good here? Why is this thing so complicated now?
Questions you should ask about the cultural shift that will happen
How the economics of the Cloud can differ from your Datacenter
What do you mean our support is now Stack Overflow?
What do you mean our goal is to move away from the CCB?
Some tangible things you can start with to help become more successful
Build that pipeline extension
Collaborate with other teams
Visibility and Monitoring
Conclusion and where you can go from here
How I (and a couple of others) successfully ran a free GitHub organization for 4000+ people and 3100
Over the last three years, I have successfully run github.com/ibm with a couple of cohorts as one of those “20%” responsibility jobs. IBM has one of the most prominent instances of a free-tier GitHub organization in the world, and dealing with this scale with such a small team has some unique challenges.
In this talk, I’ll introduce and discuss dealing with some interesting organic growth, what to do when the horse has already left the barn, and you’re attempting to corral the internal community, and how you can tend your garden (organization) without going crazy. My goal is to show you some of the ridiculous scale issues that IBM has to deal with so you can learn and prepare to maintain your organization at your scale and understand how you can defend against issues that all public GitHub organizations will eventually run into.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top