Senior AI Infrastructure Architect for LLM/ML Systems

TikTok USDS Joint Venture; Seattle (WA); On-site; USD 178,000 - 342,000; Full time

Job summary

TikTok USDS Joint Venture LLC in Seattle seeks an experienced ML/LLM infrastructure engineer to lead the design, implementation, and operation of scalable ML/LLM systems. You will collaborate across teams to drive complex engineering efforts and align technical strategies.

The role emphasizes innovation and staying at the cutting edge of LLM serving stacks, focusing on latency, throughput, and memory management while delivering reliable, high-performance systems.

Qualifications

• Bachelor's degree in Computer Science, Engineering, or a related technical discipline.
• 3+ years of hands-on experience building, training, and deploying complex and scalable Machine Learning systems.
• Strong foundation in algorithms, data structures, and software design patterns.
• Solid programming skills with a strong understanding of ML/LLM system internals.
• Proven experience in managing technical projects and delivering results.

Responsibilities

• System Architecture & Implementation: Lead the design, implementation, and operation of scalable, reliable ML/LLM infrastructure.
• Cross-Functional Collaboration: Partner effectively across teams and stakeholders to drive engineering efforts.
• Innovation: Drive technical innovation by integrating emerging technologies for cutting-edge infrastructure.

Skills

Machine Learning systems

System architecture

Cross-functional collaboration

LLM internals

Algorithms & data structures

Software design patterns

LLM serving frameworks

Project delivery

End-to-end inference optimization

Education

Bachelor's degree in CS/Engineering

Tools

vLLM

SGLang

Job description

TikTok USDS Joint Venture LLC in Seattle seeks an experienced ML/LLM infrastructure engineer to lead the design, implementation, and operation of scalable ML/LLM systems. You will collaborate across teams to drive complex engineering efforts and align technical strategies.

The role emphasizes innovation and staying at the cutting edge of LLM serving stacks, focusing on latency, throughput, and memory management while delivering reliable, high-performance systems.