Post-Training LLM Inference Platform Engineer

Advanced Micro Devices; San Jose (CA); Hybrid; USD 100,000 - 150,000; Full time

Benefits offered by this job

Comprehensive benefits

Collaborative work environment

Opportunities for career advancement

Job summary

Advanced Micro Devices is looking for a systems-minded engineer in San Jose, CA, focusing on ML infrastructure and performance optimization for large-scale model inference. Ideal candidates should have a strong background in systems engineering and experience with GPU workloads. This hybrid position offers collaboration opportunities with research teams to enhance model performance. A bachelor's or master's degree in relevant fields is required. AMD promotes a diverse and inclusive culture.

Qualifications

• Experience with GPU-accelerated workloads.
• Familiarity with LLM inference workflows.
• Solid understanding of KV cache behavior.

Responsibilities

• Research modern LLM inference frameworks.
• Design and implement KV cache lifecycle.
• Analyze and optimize performance bottlenecks.

Skills

Systems engineering

Distributed systems

ML infrastructure

Python

C++

Analytical skills

Performance optimization

Education

Bachelor's or master's degree in computer science, computer engineering, electrical engineering

Tools

Profiling tools

Open-source codebases

Job description

Advanced Micro Devices is looking for a systems-minded engineer in San Jose, CA, focusing on ML infrastructure and performance optimization for large-scale model inference. Ideal candidates should have a strong background in systems engineering and experience with GPU workloads. This hybrid position offers collaboration opportunities with research teams to enhance model performance. A bachelor's or master's degree in relevant fields is required. AMD promotes a diverse and inclusive culture.