MLOps Engineer

We are looking for our first MLops engineer to join our Research Team in order to build and maintain the foundational ML services, tooling, and automation for CPU and GPU-based algorithms. You will work in a dynamic, collaborative company culture with cutting-edge technologies. You will be responsible for our ML pipelines and infrastructure, automating and improving current flows, and more.

Responsibilities:

• Work alongside data science teams in order to understand how to optimize their processes.
• Set up and manage infrastructure for hosting machine learning models, including cloud-based platforms (e.g., AWS) and container orchestration (e.g., Kubernetes).
• Collaborate with data engineers to establish robust data pipelines for model training and inference.
• Optimize model inference post-process algorithm for high throughput and low latency.
  
  

• At least 2 years of experience as an MLops Engineer – MUST!
• Experience with machine learning frameworks (e.g., TensorFlow, PyTorch).
• Knowledge of orchestration tools like Kubernetes and Docker.
• Coding proficiency in Python programming languages.
• Desire to learn and grow as you work on a highly performant ad-serving platform.