AI Software Engineer [Remote]

Job Responsibilities:

• Extract operators (e.g. aten, triton) from AI/ML models.
• Run operators on multiple devices and collect performance data.
• Process collected data and store it to a database while maintaining data integrity.
• Implement, improve, and maintain programmatic and web interfaces to query and analyze performance data stored in the database.
• Collaborate as part of a project team to coordinate development and determine project scope and limitations.
• Review project requests to estimate time and cost required to complete the project.
• Maintain the database by ensuring data is properly saved and can be retrieved efficiently.
• Have a solid understanding of how to write data to the database and read data from it.
• After completing these tasks, integrate the database into the automated
• testing workflow (Continuous Integration - CI).

Skills:

• Hands-on experience with product-level Python programming
• Essential for implementing, improving, and maintaining programmatic and web interfaces, as well as processing and analyzing data.
• Proficiency in PyTorch, Kineto trace, dispatcher, and CUDA/Triton kernels
• Critical for extracting operators from AI/ML models, running them on devices, and collecting performance data.
• Hands-on experience in database management and SQL
• Necessary for processing collected data, storing it in databases, and maintaining data integrity.
• Machine learning experience
• Experience in Large Language Models (LLM), especially Llama
• Valuable for working with advanced AI models and potentially improving performance analysis.
• Knowledge of CI-based testing and automation
• Helpful for ensuring code quality and automating testing processes.
• Proficiency in Linux and Bash
• Important for working in the development environment and managing scripts and tools efficiently.

Education/Experience:

• At least three years of experience with above-mentioned skills is required for this role.