Building an Optimized ML Pipeline

The builders behind Superbet’s profanity detection model
Pavel Klushin
Pavel Klushin
Head of Solution Architecture at Qwak
Filip Gvardijan
Filip Gvardijan
Data Science Manager at Happening (Superbet)
Zvonimir Cikojevic'
Zvonimir Cikojevic'
ML Engineer at Happening (Superbet)
Mateja Iveta
Data Scientist at Happening (Superbet)

Qwak and members of Happening's data science and ML engineering teams discuss how they built Superbet's profanity detection model.

During this session we will discuss:

  • What best practices have been implemented for optimizing MLOps workflows and reducing operational efforts when re-deploying ML models.
  • How the team ensured fallback variations for multi-language models without duplicating efforts
  • How all this was implemented in Superbet's profanity model architecture, designed to identify profane messages in chat messages.

This session aims to provide actionable insights into how you can optimize your ML pipeline based on the team's experience.

If you're a data scientist, ML engineer, or anyone interested in learning how to optimize ML pipelines for multiple audiences, this webinar is for you. Don't miss this opportunity to learn from the experts at Happening and improve your ML pipeline.

Qwak and members of Happening's data science and ML engineering teams discuss how they built Superbet's profanity detection model.

During this session we will discuss:

  • What best practices have been implemented for optimizing MLOps workflows and reducing operational efforts when re-deploying ML models.
  • How the team ensured fallback variations for multi-language models without duplicating efforts
  • How all this was implemented in Superbet's profanity model architecture, designed to identify profane messages in chat messages.

This session aims to provide actionable insights into how you can optimize your ML pipeline based on the team's experience.

If you're a data scientist, ML engineer, or anyone interested in learning how to optimize ML pipelines for multiple audiences, this webinar is for you. Don't miss this opportunity to learn from the experts at Happening and improve your ML pipeline.

Qwak optimizes ML Model Production

“We ditched our in-house ML platform for Qwak. I wish we had found them sooner.”
Upside
“Qwak streamlines ML development from prototype to production, freeing us from infrastructure concerns and maximizing our focus on business value.”
Notion
“People ask me how I managed to deploy so many models while onboarding a new team within a year. My answer is: Qwak.”
OpenWeb
“With Qwak, our ML team efficiently manages and deploys various models, both batch and real-time. The addition of an observability and Vector DB layer has been a game-changer, allowing us to confidently bring 10 models into production. Qwak's robust and streamlined approach has significantly enhanced our operational efficiency.”
Happening (Superbet)