Akamai Technologies

Performance Engineer – Akamai Inference Cloud

Akamai Technologies

full-time

Posted on:

Location Type: Remote

Location: Remote • 🇵🇱 Poland

Visit company website
AI Apply
Apply

Job Level

Mid-LevelSenior

Tech Stack

Distributed Systems

About the role

  • The Performance Engineer ensures optimal benchmarking, tuning, and performance of an AI inference platform.
  • Responsibilities include applying advanced optimization techniques to enhance throughput, reduce latency, and improve resource efficiency.
  • The role involves working with models, hardware accelerators, and infrastructure.
  • Expertise in AI/ML performance optimization, proficiency with inference frameworks, and a passion for maximizing hardware and software performance are essential.

Requirements

  • Have experience in performance engineering with hands-on expertise in AI/ML model optimization and inference performance tuning.
  • Demonstrate solid knowledge of inference optimization techniques including quantization (INT8, FP16), model compilation, hardware acceleration, and familiarity with compiler optimizations and ML compilers.
  • Show proficiency with GPU optimization and understanding of memory hierarchies and techniques to maximize hardware utilization.
  • Have experience with profiling and benchmarking tools for AI workloads, identifying performance bottlenecks in distributed systems.
  • Demonstrate problem-solving skills with ability to analyze performance data, communicate insights clearly, and drive optimization efforts.
  • Possess knowledge of distributed inference and model parallelism techniques.
  • Have experience with cost optimization for compute-intensive workloads.
Benefits
  • Your health
  • Your finances
  • Your family
  • Your time at work
  • Your time pursuing other endeavors

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard skills
performance engineeringAI/ML model optimizationinference performance tuninginference optimization techniquesquantizationmodel compilationhardware accelerationGPU optimizationprofiling toolsbenchmarking tools
Soft skills
problem-solvingdata analysiscommunication