Veronika Kolesnikova
Senior Software Engineer, Microsoft MVP (AI)
Boston, Massachusetts, United States
Actions
Software engineer by day and AI enthusiast by night. Veronika has extensive experience in full-stack development using C#, .NET, Java and Typescript, Azure and AWS clouds. Public speaker, hackathon volunteer, co-organizer of Boston Azure AI user group, and mentor. Curious about Augmented Reality.
Veronika holds a master's degree in Information Technology. She likes dancing, traveling and practicing aerial fitness in her free time.
Links
Badges
Area of Expertise
Topics
The power of multimodal models
AI is everywhere and its tasks are getting more and more complex. At the same time performance has to keep up as it plays significant role in deployed solutions.
When passing prompts, custom data and completions between models sounds like a disaster, multimodal models are coming to the rescue. Let's dive into the world of AI starting from an overview of AI in general and then getting familiar with all the terms, models and tasks they can help us with. Then we'll dive deeper into a fascinated world of vision language models: learn about underlying architecture and techniques of those models.
The talk will also highlight the practical applications of vision language models in real-world scenarios. In the end I'll show a demo using one of the latest vision language models for detecting specific features of an object in a picture.
Evaluate your model and prompt using AI Foundry
Too many models? How to choose the right one? What's the best prompt for this model? AI Foundry evaluation tools can help you out. No need to switch between the code and visuals, you don't even need to have the code at all. AI Foundry Evaluation tools are a fast and user-friendly approach to all your evaluations. Perfect for data scientists, machine learning engineers, and AI enthusiasts, this session will empower you to elevate your AI projects to the next level.
Responsible AI and Content Safety
Nowadays with the development of AI, it became a big part of our lives. It started with statistics, so was focused mostly on numbers: precision, recall, etc. But at some point, it became obvious lots of AI models were missing something very important: responsibility.
Content Safety got everyone's attention with increasing popularity of Generative AI. How to protect both inputs and outputs? What can be done other than prompt engineering? Content Safety detects harmful user-generated and AI-generated content in applications and services and can help you with putting guardrails around your Generative AI models.
Let's discuss the principles of Responsible AI and some tools to support AI developers. In this session we will talk about AI and ML in general, data preparation, Responsible AI and Content Safety principles and tools. In the end, I will show a demo using some of the tools supported by Azure AI.
Langchain vs prompt engineering: real life observations
Langchain and similar open source frameworks for building language model based applications are probably as popular as those language models: ChatGPT, GPT-4, etc. But how approachable and useful those frameworks are? At the same time prompt engineering presented as something that can be easily implemented, used by non-developers and developers alike and light-weight. How powerful is it?
Let's talk about scenarios when it's better to use Langchain and when a good prompt can be enough. I will use my personal projects as examples, and the attendees are welcome to share their experience as well.
Responsible AI
Nowadays with the development of AI, it became a big part of our lives. It started with statistics, so was focused mostly on numbers: precision, recall, etc. But at some point, it became obvious lots of AI models were missing something very important: responsibility.
Microsoft came up with basic principles of Responsible AI and provided some tools to support AI developers. In this session we will talk about AI and ML in general, data preparation and Responsible AI principles and tools. In the end, I will show a demo using some of the tools inside Azure ML.
KCDC 2023 Sessionize Event
Festive Tech Calendar 2022 Sessionize Event
TechBash 2022 Sessionize Event
Visual Studio Live! New Orleans, Boston & Microsoft HQ 2019 Sessionize Event
Xamarin Developer Summit Sessionize Event
Veronika Kolesnikova
Senior Software Engineer, Microsoft MVP (AI)
Boston, Massachusetts, United States
Links
Actions
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