Remote AI Inference Engineer - Cloud Runtime

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

Benefits offered by this job

FlexBase program

Job summary

Akamai Technologies GmbH in Kraków is hiring a Software Engineer for the Inference Cloud team. You will build and optimize AI inference pipelines, handle prompt processing and tokenization, and improve model serving infrastructure for low-latency workloads.

You will collaborate with experienced engineers on model architectures, runtimes, and deployment frameworks. Strong Python experience and familiarity with C++, Go, or Rust are valued, along with Linux and container-based environments.

Qualifications

• Proven experience with Python and at least one systems language (C++, Go, or Rust).
• Understanding of NLP concepts like tokenization, encoding, and text processing pipelines.

Responsibilities

• Develop and maintain prompt processing and tokenization pipelines for inference requests.
• Implement routing, scheduling, and batching to optimize throughput and latency.
• Integrate new model architectures and backends into the runtime framework.
• Write well-tested, documented code and participate in code reviews.

Skills

Python

C++

Go

Rust

NLP basics

AI inference

Linux

Containers

Profiling tools

Tools

TensorRT

vLLM

TorchServe

Triton

Job description

Akamai Technologies GmbH in Kraków is hiring a Software Engineer for the Inference Cloud team. You will build and optimize AI inference pipelines, handle prompt processing and tokenization, and improve model serving infrastructure for low-latency workloads.

You will collaborate with experienced engineers on model architectures, runtimes, and deployment frameworks. Strong Python experience and familiarity with C++, Go, or Rust are valued, along with Linux and container-based environments.