AI Systems Performance Specialist

Job Summary

We are seeking an AI Systems Performance Specialist to optimize AI training and inference workloads for maximum performance, scalability, and cost efficiency. The ideal candidate will have expertise in GPU optimization, distributed training, LLM inference, Python, C++, and ML systems performance, with a strong background in production AI workloads.

Key Responsibilities

• Optimize AI training and inference pipelines for throughput, latency, and cost
• Improve GPU utilization, memory management, and distributed training performance
• Implement model optimization techniques including quantization, pruning, and batching
• Build benchmarking, profiling, and performance monitoring solutions
• Collaborate with ML and platform teams to improve AI system efficiency
• Evaluate new AI hardware, software, and performance optimization strategies

Required Qualifications

• 6+ years of experience in performance engineering, ML systems, or HPC
• Strong proficiency in Python and C++
• Hands-on experience with GPU optimization, distributed training, and deep learning workloads
• Experience with profiling tools, model optimization, and AI performance tuning

Preferred Qualifications

• Experience optimizing production-scale LLM inference
• Familiarity with vLLM, TensorRT-LLM, DeepSpeed, Triton, or CUTLASS
• Experience with AI infrastructure cost optimization (FinOps) or AI systems research