From DevOps to MLOps: Scaling ML models to 2 Million+ requests per day

The challenge with Machine Learning (ML) models is productionizing. It requires data ingestion, data preparation, model training, model deployment, and monitoring.Adopting MLOps practices is similar to DevOps practices. In MLOps, the workload changes, but some core principles like automation, continuous integration/continuous deployment (CI/CD), and monitoring. Taking DevOps practices, I will discuss the similarities and differences in adopting MLOps practices.In this talk, Chinmay takes a production use case to scale ML models to 2 million+ daily requests. It leverages Google Cloud's (GCP) infrastructure to use its GPU and other services. This talk will help you draw similarities between DevOps and MLOps as a DevOps practitioner and help you learn how to run Machine Learning models at the production scale with best practices.

Related Talks

Demo: Intro to Local AWS Development via LocalStack

How much faster could your cloud application release cycles move if your developers didn’t need to deploy code to the cloud?

Local cloud development eliminates the security implications, cost concerns, and access restrictions of traditional cloud development by replicating production-quality application environments on local infrastructure.

Join us on Tuesday, December 16, at 1pm eastern time for a live demo webinar to learn more about:

  • How LocalStack replicates production-quality AWS application environments on local infrastructure
  • The unique advantages that local cloud environments provide for software developers
  • Successful use cases where local cloud development unlocks velocity that developers can’t experience on the cloud

Even if you’re not available to join the livestream, sign-up here to receive the session recording in your inbox.

Learn More
Learn More
Autonomous Bug Fixing Through AI Agents That Detect, Reproduce, and Repair

What if your software could fix its own bugs—before anyone even notices them? In this session, LogicStar co-founder Boris Paskalev shares how self-healing applications are becoming a reality—fixing bugs automatically, before they reach production or immediately after an issue is detected/reported. LogicStar combines classical computer science, deep tech research from the pioneers of “AI for Code” and Agentic AI to detect, reproduce, and fix real production issues with validated, test-backed pull requests.This session is for engineering leaders, PMs, and AI builders ready to rethink the boundaries of autonomy in software delivery.

Learn More
Learn More
Creating self-healing software systems via effective usage of telemetry data and AI agents

Modern software systems operate in complex, dynamic environments where failures are inevitable. Traditional monitoring and manual incident response are no longer sufficient to ensure resilience or customer satisfaction. This talk explores how to design and implement self-healing software systems by combining telemetry data with an AI-driven agentic approach. We’ll start by examining how high-quality telemetry forms the foundation for detecting anomalies and predicting failures. Next, we’ll show how modern GenAI (LLMs) can transform this telemetry into actionable insights for AI agents that interpret data, pinpoint root causes, and apply automated fixes. Through a practical, real-world example, you’ll see how telemetry and AI work together to create adaptive feedback loops that continuously improve system reliability, while freeing engineers from repetitive operational tasks.

Learn More
Learn More

Launch yourself in the world of local cloud development

Try for free
Try for free
Talk to Sales
Talk to Sales