Software Engineer (AI)

TL;DR

Software Engineer (AI): Building and optimizing LLM serving infrastructure with an accent on GPU performance and disaggregated serving architectures. Focus on profiling, benchmarking, and enhancing the serving stack to ensure high-efficiency model deployment.

Location: Must be based in Sunnyvale, CA or Seattle, WA, USA

Salary: $207,000–$301,000

What you will do

• Design and implement disaggregated serving architectures for large language models.
• Enhance the LLM serving stack to improve throughput and latency.
• Profile and benchmark LLM models on GPU accelerators to identify performance bottlenecks.
• Build custom performance analysis tooling to monitor system efficiency.
• Collaborate with research and SRE teams to deploy LLMs into production environments.

Requirements

• Must be based in Sunnyvale, CA or Seattle, WA, USA.
• Strong experience in distributed computing and performance profiling.
• Deep understanding of GPU acceleration and LLM serving stacks.
• Proficiency in benchmarking and debugging complex machine learning systems.
• Ability to work effectively with cross-functional research and engineering teams.