MLOps Engineer - Praha | TV Nova

MLOps Engineer

Odpovědět na inzerát

První česká soukromá celoplošná televize Nova zahájila své vysílání přenosem z Národního muzea v Praze dne 4. 2. 1994. Od té doby jsme prošli celou řadou změn a dnes jsme jednou z nejmodernějších mediálních společností na českém trhu. Za tím vším stojí společenství lidí, kteří pracují v nejrůznějších profesích, ať už specificky televizních nebo těch ostatních, podporujících. Milují svoji práci, snaží se v ní být každý den nejlepší a přicházet stále s novými nápady. Nahrávají si vzájemně, podporují se a makají na sobě.

Lokalita

Praha

Typ spolupráce

Pracovní smlouva


About 

Combining the world of entertainment and data science can be something truly special: where else could you influence what gets broadcast on the most-watched TV station or what new content appears on Oneplay? We are the largest commercial TV network in Central Europe and video platform with largest number of subscribers in Czechia. We are now looking for someone to expand our AI/ML team and help us take AI in the company to the next level. 

The Mission

You are the bridge between our data science models and our viewers. Your mission is to help maintain and optimize our existing batch-processing pipelines (Databricks/PySpark), while actively contributing to building low-latency containerized serving systems (Docker/Kubernetes), where they needed. 

What will you do? 

  • Partner with the AI and ML teams to package, optimize, and deploy their Python, PySpark, and PyTorch models into production. 
  • Help execute our migration from batch processing on Databricks to live, real-time inference systems running on Kubernetes (AKS and AWS equivalents). 
  • Work with high-performance serving frameworks (e.g., Triton, ONNX Runtime, TorchServe) to ensure low-latency model execution. 
  • Build, maintain, and monitor containerized ML applications across our multi-cloud infrastructure (AWS, Azure). 
  • Maintain and improve our CI/CD pipelines using GitHub Actions and GitLab CI, ensuring models are tested and deployed reliably. 
  • Uphold our engineering standards by participating in code reviews, writing clear documentation, and adhering to strict code quality guidelines. 

What do we require? 

  • Proven track record of designing and managing high-availability production systems using Docker and K8.  
  • Strong programming skills in Python and a solid understanding of ML frameworks, particularly PyTorch and PySpark. 
  • Experience or strong interest in compiled languages used for high-performance backend (e.g., Go, Rust, or C++). 
  • Hands-on experience with containerization and orchestration using Docker and Kubernetes. 
  • Experience operating in cloud environments (AWS or Azure) and familiarity with Databricks. 
  • Practical knowledge of setting up and maintaining CI/CD pipelines using GitHub Actions or GitLab CI. 
  • A strong software engineering mindset with a dedication to code reviews, documentation, and automated testing. 
  • Familiarity with model compilation/optimization (ONNX, TensorRT) is a bonus. 

Why work in our ML team?

  • We do truly innovative things in the online and linear media world (RecSys, causal inference, GenAI). 
  • We run projects with real business impact. 
  • Your opinion matters – you'll be part of the full development cycle. 
  • We enjoy what we do because our work is meaningful. 

What we offer: 

  • Praticipation on AI/ML conferences (paid by a company),  
  • A pleasant work environment, a down-to-earth team, and good coffee. 
  • A hybrid work model. 
  • 5 weeks of vacation and 8 additional days off per year. 
  • Competitive salary and a generous benefits package.