AI Infrastructure Engineer (LLM)

About the role

Shuru is an AI-native technology and engineering services company helping businesses build and scale high-impact products and AI solutions. It is looking for an LLM / AI Infrastructure Engineer to deploy, optimize and operate open-source Large Language Models in a secure private cloud or on-premise environment, without relying on public black-box APIs. The role works closely with a Turkish entity and an international architecture team to integrate LLM capabilities into a production MVP while meeting strict privacy, security and regulatory requirements.

Key responsibilities

• Deploy and manage open-source LLMs such as Llama, Mistral, Qwen or similar models.
• Fine-tune and adapt models for business-specific use cases.
• Optimize LLM inference for performance, latency, memory usage and cost.
• Set up and operate models in private cloud, on-premise or bare-metal environments.
• Integrate LLM services into a production-ready MVP through APIs and backend services.
• Implement secure model-serving and data-processing workflows.
• Ensure AI infrastructure complies with data privacy, security and regulatory requirements.
• Monitor model performance, infrastructure utilization and production reliability.
• Collaborate with architecture, engineering and business teams across Turkey and international locations.

Required profile

• Strong hands-on experience deploying open-source LLMs in production.
• Experience with model fine-tuning, inference, quantization and optimization.
• Experience with private cloud, on-premise or bare-metal infrastructure.
• Professional proficiency in Turkish and English.

Required skills

• GPU infrastructure and model serving.
• vLLM, Hugging Face, PyTorch, TensorRT-LLM, llama.cpp or similar tools.
• Docker, Kubernetes, Linux and production AI/ML infrastructure.
• Data privacy, security and regulatory compliance understanding.

What we offer

• Work on challenging, large-scale engineering and data problems.
• Closely work with experienced engineering, product and technology leaders.
• Opportunity to take ownership of architecture and key technical decisions.
• Remote-first and collaborative work environment.
• Strong opportunities for learning, leadership and career growth.