AI Inference Performance Engineer — Remote (Poland)

Akamai Technologies GmbH; Remote; PLN 120,000 - 180,000; Full time

Job summary

A leading technology company is looking for a Performance Engineer to optimize AI inference platforms. Responsibilities include benchmarking AI models, implementing optimization techniques, and collaborating with engineering teams. Successful candidates will have expertise in AI/ML performance and GPU optimization. This role also offers flexible working options, allowing you to work from home or the office in Poland.

Benefits

Flexible working options

Health benefits

Family support options

Qualifications

• Experience in performance engineering with AI/ML model optimization and inference tuning.
• Knowledge of inference optimization techniques including quantization and model compilation.
• Proficiency with GPU optimization and understanding of memory hierarchies.

Responsibilities

• Benchmarking and profiling AI models and measuring performance metrics.
• Researching and implementing model optimization techniques.
• Collaborating with engineering teams for optimization recommendations.

Skills

AI/ML performance optimization

Inference frameworks

GPU optimization

Problem-solving skills

Benchmarking and profiling tools

Tools

TensorRT

Triton

TorchServe

Job description

A leading technology company is looking for a Performance Engineer to optimize AI inference platforms. Responsibilities include benchmarking AI models, implementing optimization techniques, and collaborating with engineering teams. Successful candidates will have expertise in AI/ML performance and GPU optimization. This role also offers flexible working options, allowing you to work from home or the office in Poland.