Apple

I lead the data science and engineering team at Apple Services Finance. The team focuses on translating business problems and requirements into data products using advanced statistical and machine learning models to support and help Apple leadership make data-driven decisions.

Senior Manager - Data Science and Engineering 

Managing a data science team focusing on cost optimization on Apple infrastructures with the use of statistical analysis and machine learning models.

Data Science Manager

Senior Data Scientist

Ernst & Young

Predictive analysis, time series models, forecasting and machine learning

Data Scientist

University of Michigan Law School

Data Analyst supporting the Empirical Legal Studies Center
Prediction Models, Regression Analysis and Data Visualization using R, JMP and Stata.

University of Michigan

Data Manipulation & Cleansing of a large database (India Census) using Stata and R
GIS Analysis with R
Data Visualization

Data Analyst

Senior Manager - Data Science and Engineering at Apple

I lead the data science and engineering team at Apple Finance - Services and Infra. The team focuses on translating business problems and requirements into data products using advanced statistical and machine learning models to support and help Apple leadership make data-driven decisions.

I am also an open-source contributor and the author of Hands-On Time Series Analysis with R (Packt publication) and several R packages for time series analysis and machine learning applications. Currently working on my next book, Applied Time Series Analysis and Forecasting, which focuses on forecasting at scale. 

Also available on:
Github: https://github.com/RamiKrispin
Medium: https://medium.com/@rami.krispin
Mastodon: https://mstdn.social/@ramikrispin

SQL Agents with Large Language Models 🚀

I’m thrilled to share my new LinkedIn Learning course — SQL Agents with Large Language Models!

The term AI agent might sound fancy, but at its core, it’s simply a set of functions that take a user question or request, process it with an LLM, and return an answer.

In this course, we’ll break down the components of an SQL AI agent and build one from scratch. Here’s what we’ll cover:
 ➡️ SQL AI agent architecture – how AI agents work and the components of a basic SQL AI agent
 ➡️ Working with LLM APIs – how to send prompts to LLM providers like OpenAI, Google Gemini, and Anthropic Claude, and how to run models locally with Docker Model Runner using the OpenAI Python SDK
 ➡️ Prompt engineering – how to design and optimize prompts for generating SQL, and how to automate prompt creation with templates
 ➡️ Building the SQL AI agent – connecting all components into a complete working system

This course is beginner-friendly and assumes no prior knowledge of AI agents.

A huge thank-you 🙏🏼 to the amazing LinkedIn for Learning team for supporting this course from ideation to recording — especially producer Emanuel Garcia and content manager Jennifer Brady!

Here’s a sneak peek at the course:
https://lnkd.in/gZBdz3tu

Rami Krispin

Senior Manager - Data Science and Engineering at Apple | Docker Captain | LinkedIn Learning Instructor

SQL agent architecture: LLM database integration design patterns

My weekend reading - Time Series Forecasting Using Foundation Models by Marco Peixeiro 👇🏼

#timeseries #ai #forecasting

No alternative text description for this image

GitHub Spec-Kit 🚀

GitHub recently released a new project - Spec-Kit, an open-source project that aims to supplement AI code generation tools such as Claude Code, OpenAI Codex, etc. 

If you are using Vibe coding, you spend some time creating the required context and instructions to enable the AI code generator to be efficient and accurate. Spec-Kit aims to make this process efficient by creating a project spec based on the user input. This includes tools for:
🔹 Define the project's governing principles and development guidelines that will guide all subsequent development
🔹 Create the project spec to describe what you want to build
🔹 Create a technical implementation plan
🔹 Create an actionable task list from your implementation plan.

🔗: https://lnkd.in/gFGAgqMx

#ai #github #opensource

I share a weekly curated update on data science and engineering topics and resources.

This week's agenda:
🔹 Open Source of the Week - The TimeCopilot Project
🔹 New learning resources - LLM & RAG evaluation playbook, git course, deploy AI app to Hugging Face Spaces, n8n tutorials, building LLMs from Scratch
🔹 Book of the week - Modern Deep Learning Foundations by Dr. Barak Or

♻️ Please share if you find it useful!
📌 Join 30k subscribers and subscribe for weekly updates.

#datascience #ai #machinelearning

Hi folks, Last week, this newsletter reached its 1st anniversary. What started as an experiment is now updated weekly. I want to thank each of you for

Open article: The TimeCopilot Project, Modern Deep Learning Foundations Book, New Tutorials  by Rami Krispin • 4 min read

The TimeCopilot Project, Modern Deep Learning Foundations Book, New Tutorials

Taplio

Rami Krispin's Linkedin Analytics

Who is engaging with Rami

's Best Posts (last 30 days)

Want to drive more opportunities from LinkedIn?

Taplio

.css-1jgreyo{background-image:linear-gradient(284deg, rgba(39,43,72,1) 0%, rgba(33,47,183,1) 100%);color:transparent;-webkit-background-clip:text;background-clip:text;}Rami Krispin's Linkedin Analytics

Who is engaging with Rami

's Best Posts .css-qqfgvy{font-size:var(--chakra-fontSizes-md);}(last 30 days)

Want to drive more opportunities from LinkedIn?

Rami Krispin's Linkedin Analytics

's Best Posts (last 30 days)