AI Infrastructure Engineer

• Develop and maintain software tools and frameworks for deploying AI models on specialized hardware.
• Deploy and optimize AI models in HPC and Cloud environments.
• Work on multi-node and multi-GPU deployment scenarios.
• Optimize Scale-Up and Scale-Out solutions for AI workloads.
• Profile and analyze AI application performance.
• Collaborate closely with hardware, systems, and AI teams to optimize end-to-end solutions.
• Contribute to continuous improvement of AI deployment architecture, tools, and workflows.

• 8+ years of experience in a similar role (AI Infrastructure / AI Systems / HPC).
• Hands-on experience with AI model deployment frameworks such as vLLM, SGLang, Triton, DeepSpeed .
• Experience with AI model serving in HPC and/or Cloud environments .
• Strong background in multi-node and multi-GPU deployment and optimization .
• Experience with Scale-Up and Scale-Out solutions .
• Strong problem-solving skills and attention to detail.
• English proficiency at C1 level or higher .
• Bachelor's, Master's, or PhD degree in a relevant field.

Nice to have:

• Experience with TensorRT and ONNX Runtime .
• Experience with CUDA and/or ROCm .
• Experience with TensorFlow .
• Strong C++ skills.
• Experience with C/C++ and Python interoperability .
• Assembly-level programming experience.
• Bare-metal programming experience.
• Software profiling and architecture-based optimization.
• Master's or PhD degree.

• Permanent, full-time onsite role in Barcelona, Spain .
• Flexible working hours (Monday-Friday, 9:00-18:00).
• Work in one of the few European companies building AI chip infrastructure end-to-end.
• Small, highly skilled team with strong technical ownership and impact.
• Supportive, family-friendly work environment.
• Candies, coffee, and free Spanish lessons

AUTSORSA is a fast-growing company founded and based in Bulgaria, providing business outsourcing, outstaffing, and HR services to clients all over the world. Our client is a leading European semiconductor company developing cutting-edge AI chip infrastructure and software platforms that enable high-performance AI and data processing workloads. Their teams work end-to-end - from hardware architecture to low-level software - building complete solutions that power next-generation AI systems. If you are passionate about AI infrastructure, scalable deployment solutions, and AI model optimization in HPC and Cloud environments, and want to work closely with hardware and AI teams on real-world, high-impact products, this is a great opportunity to join a fast-paced and innovative environment. We are looking for an AI Infrastructure Engineer with experience in AI model deployment in HPC/Cloud provider environments to join the team. If you have a passion for AI and want to help bring the future of AI acceleration to market, you'll find the right challenges with us.