Infrastructure Engineer (AI Inference)

Location: San Francisco, California; remote within the United States may be considered for exceptional candidates

Salary: $200,000–$400,000 per year plus equity

Company

hirify.global develops infrastructure around vLLM to make AI inference cheaper, faster, and more reliable.

What you will do

• Build distributed systems and foundational infrastructure for serving models through vLLM at global scale.
• Design systems that support inference across thousands of accelerators with low latency and high reliability.
• Develop high-performance systems using Rust, Go, or C++.
• Work with network protocols, high-performance I/O, GPU programming models, and memory hierarchies.
• Debug complex distributed systems issues and improve system performance and reliability.

Requirements

• Bachelor’s degree or equivalent experience in computer science, engineering, or a similar field.
• Strong systems programming skills in Rust, Go, or C++.
• Experience designing and building high-performance distributed systems at scale.
• Understanding of network protocols and high-performance I/O.
• Ability to debug complex distributed systems issues.
• Work from the United States is required for remote candidates; the primary location is San Francisco.

Nice to have

• Experience with ML serving infrastructure and disaggregated inference architecture.
• Familiarity with GPU programming models, memory hierarchies, and GPU interconnects such as NVLink, InfiniBand, or RoCE.
• Experience supporting large-scale model training or inference environments.
• Track record of improving system reliability and performance at scale.

Culture & Benefits

• Health, dental, and vision benefits.
• 401(k) company match.
• Equity included in the compensation package.
• Visa sponsorship is available on a case-by-case basis.