Lead AI Inference Framework Architect

Samsungsemiconductor; San Jose (CA); On-site; USD 219,000 - 351,000; Full time

Benefits offered by this job

4+ weeks of paid time off per year

Medical/Dental/Vision/401k

Flexible work environment

Onsite Café and gym

Job summary

Samsung Semiconductor is looking for a Principal Engineer, AI Serving Framework Architect in San Jose. You will lead research teams and innovate methodologies for AI inference performance. The ideal candidate holds a PhD and has extensive experience in AI Serving Frameworks.

Be part of a team offering a flexible work environment, diverse benefits, and a commitment to equal opportunity employment.

Qualifications

• 10+ years of experience in AI Serving Framework for large-scale computing focused on AI workloads.
• Led a project to optimize a Large Language Model Inference Software Stack.
• Strong understanding of compute, memory, and networking bottlenecks in AI systems.

Responsibilities

• Lead research teams in Korea and propose technical direction.
• Research dynamic scheduling methodologies for AI inference performance.
• Investigate methods to accelerate search operations in RAG’s vector DB.

Skills

PyTorch

Python

C++

Education

PhD in Computer Science or a related field

Job description

Samsung Semiconductor is looking for a Principal Engineer, AI Serving Framework Architect in San Jose. You will lead research teams and innovate methodologies for AI inference performance. The ideal candidate holds a PhD and has extensive experience in AI Serving Frameworks.

Be part of a team offering a flexible work environment, diverse benefits, and a commitment to equal opportunity employment.