We are looking for an AI Inference Engineer to join our technologically international engineering environment, who wants to participate in the development and optimization of production AI systems for operating large models including LLM. You will work on performance-critical AI solutions, optimizing the inference pipeline, and collaborating with top specialists in software, hardware, and artificial intelligence. You will tackle real technical challenges from model deployment to scaling and performance optimization.

• design and optimize inference pipelines for large AI models and LLMs
• work with frameworks such as PyTorch, TensorRT, and vLLM
• implement and optimize ML models using techniques like INT8/FP8 quantization, kernel fusion, and efficient batching
• optimize key ML operators, such as GEMM operations, convolutions, and activation functions
• troubleshoot performance issues using system tuning and performance analysis
• test, deploy, and scale AI systems in production environments
• work with modern hardware including GPUs and AI accelerators
• collaborate on the design of high-performance software solutions
• contribute to improving the performance, stability, and efficiency of AI platforms
• collaborate with AI, software, and platform engineering teams in an international environment

• Master's degree in computer science, engineering, mathematics, or a related field
• very good knowledge of programming in C/C++ or Python
• experience with development in a Linux environment
• good knowledge of computer architecture, data structures, and system software
• practical experience with implementing algorithms in C, C++ or Python
• experience with accelerated hardware, such as GPUs, FPGAs, DSPs, or AI accelerators
• knowledge of CUDA, OpenCL, or similar frameworks
• experience in designing or developing high-performance systems
• good orientation in the field of machine learning and AI
• ability to analyze and solve complex technical problems
• independence, responsibility, and team spirit
• English at a communicative level

• Experience with LLM, inference optimization, TensorRT, vLLM, or performance optimization of models on GPUs is an advantage.

• We are a reliable and stable company with an international reach
• In case of project termination, we immediately offer another one
• We have projects from more than 200 different companies
• We guarantee timely invoice payments and minimal administration
• We organize great corporate events for our entire IT community
• We provide free accounting and tax consulting
• We pride ourselves on a personal approach and fairness, you can rely on us