Job Description

xAI is seeking a highly motivated Software Engineer to architect and implement scalable distributed infrastructure for model serving, ensuring reliability, creating custom debugging tools, and developing robust CI/CD infrastructure. The ideal candidate will have experience with large-scale production serving and GPU inference engines.

Responsibilities

• Architect and implement scalable distributed infrastructure for model serving
• Ensure reliability of inference services
• Create custom tools for tracing, replaying, and fixing issues
• Benchmark and fine-tune inference engines
• Develop robust CI/CD infrastructure

Requirements

• Experience with large-scale, high-concurrent production serving
• Experience with GPU inference engines
• Experience with testing, benchmarking, and reliability of inference services
• Experience with designing and implementing CI/CD infrastructure
• Strong communication skills

Benefits

• No benefits