Researcher: Inference - Remote

Overview

This role involves conducting cutting-edge research to enhance the efficiency and robustness of inference for AI models across various modalities.

In Short

• Conduct research to improve AI model inference efficiency.
• Design and optimize inference pipelines for various environments.
• Develop techniques for efficient model execution.
• Explore advanced methods to reduce inference latency.
• Investigate trade-offs between model quality and efficiency.
• Prototype methods for stateful and streaming inference.
• Collaborate with teams to integrate research into production.

Requirements

• Expertise in optimizing inference for machine learning models.
• Strong programming skills in Python and experience with AI frameworks.
• Knowledge of hardware architectures and their impact on performance.
• Experience in designing low-latency inference pipelines.
• Understanding of the trade-offs in model deployment.
• Problem-solving skills and passion for innovative techniques.

Benefits

• Lunch, dinner, and snacks provided at the office.
• Fully covered medical, dental, and vision insurance.
• Pension plan available.
• Relocation and immigration support offered.
• Inclusive and supportive team culture.