Senior Software Engineer, TPU Performance, Hardware/Software Co-Design

Requirements

• Bachelor’s degree or equivalent practical experience.
• 5 years of coding experience in one or more of the following languages: C, C++, Java, or Python.
• 5 years of experience testing, maintaining, or launching software products.
• 5 years of experience with software development in one or more programming languages.

Nice to Haves

• Experience with architecture simulator development and microarchitecture.
• Experience with data structures or algorithms.
• Experience focused on ML algorithm and performance analysis and optimization.
• Experience with Large Language Models and ML frameworks and compilers.
• Knowledge of computer architecture such as TPU's or other accelerators.
• Excellent communication skills.

What You'll Be Doing

• Analyze performance, power, and energy efficiency of current and future Machine Learning workloads to identify issues.
• Enable the peak efficiency of future and current ML systems through full-stack ML hardware or software co-design by proposing hardware-aware algorithm optimization and related simulation modeling.
• Establish an understanding of the latest business-critical production ML models (e.g., large-language models, large embedding models) to inform optimizations of model architecture, software systems, and hardware architecture.

Perks and Benefits

• Flexible working hours.
• Competitive salary and bonus package.
• Healthcare and dental insurance coverage.
• Paid time off and holidays.
• Professional development opportunities.