Performance Engineer: AI Inference & Systems (LLM)

RadixArk; Palo Alto (CA); On-site; USD 120,000 - 160,000; Full time

Benefits offered by this job

Competitive compensation

Comprehensive health benefits

Flexible work arrangements

Job summary

RadixArk is seeking a Performance Engineer in Palo Alto, CA to improve performance in AI workloads. You'll work on optimizing various aspects of AI systems, ensuring they are reliable and efficient.

Ideal candidates have a strong systems engineering background, experience with GPU systems, and the ability to debug performance issues across multiple layers. RadixArk offers competitive compensation and flexible working arrangements.

Qualifications

• Experience in performance-critical software engineering.
• Familiarity with GPU systems and cloud environments.
• Strong communication skills to translate complex issues.

Responsibilities

• Optimize performance across production deployments.
• Benchmark workloads for AI models.
• Investigate performance regressions in real environments.

Skills

Performance-critical software

GPU systems

Distributed systems

Machine learning runtimes

Python

C++

Performance debugging

Profiling tools

Tools

CUDA

Triton

Pallas

ROCm

XLA

Job description

RadixArk is seeking a Performance Engineer in Palo Alto, CA to improve performance in AI workloads. You'll work on optimizing various aspects of AI systems, ensuring they are reliable and efficient.

Ideal candidates have a strong systems engineering background, experience with GPU systems, and the ability to debug performance issues across multiple layers. RadixArk offers competitive compensation and flexible working arrangements.