Join Milestone and build technology that pushes boundaries and empowers businesses worldwide.Impact & PurposeDo you want to contribute to the AI computer vision of 2026 and beyond? If you envision that your next role will shape the future of visual machine learning and do it responsibly and with real-world impact then please keep reading!Location: Copenhagen (Hybrid)Role SummaryAs a Senior Cloud Engineer in Hafnia, you will be responsible for setting up and preparing our operation in data centers and AI factories. Your expertise will blend system admin and cloud vision to make Hafnia services available and secure in compute powerhouse as well as on prem servers. You will become a member in our cross-functional team to drive model deployments, ensuring best practices and compliance with industry standards.What you will doTest and define requirements for data centers and on-prem servers alike, including GPU servers, storage, networking, IAM, and ML hardwareDeploy and maintain VLM inference environments, ensuring replicability, stability, security, and high performanceDefine, build and manage local model serving platforms, including load balancing, autoscaling, GPU scheduling, and observabilityImplement infrastructure automation for provisioning, configuration, and monitoring of compute clustersOptimize hardware utilization, latency, throughput, and memory footprint for ML inference workloadsCollaborate with our Computer vision exports to support model integration, upgrades and environment customization.Ensure data security, access control, and compliance across environments hostingWhat you bring to the teamDeep expertise in server hardware, including GPUs (NVIDIA A/H-series), NICs, storage buses etc.Advanced knowledge in Linux systems engineering, low level debugging and optimizationExpertise with containerization & orchestration (Docker, Kubernetes, K8s GPU operators)Solid understanding of MLOps infrastructure, including model serving, GPU scheduling, caching, quantization, and monitoring.Knowledge of on prem deployment automation and deploymentAbility to optimize inference/runtime performance through GPU tuning, quantization, and rightsizing models.Comfortable working across hardware, OS, network, and ML layersSharp production of documentation, runbooks, monitoring dashboards, and operational processes for ML systems.How will you make a difference5+ years in infrastructure, cloud, or systems engineering, including hands-on management of computer hardware and background in storage, networking, and eventually virtualization for data intensive ML workloads.Experience running GPU accelerated clusters, ML training servers, or on prem AI/LLM deployments at scale.Track record deploying LLMs or VLMs in both online and offline environments with strict security/compliance constraints.Experience building high availability, high throughput compute environments for AI workloads.About our teamYou will join about 35 fantastic colleagues in a fast-growing and international team that besides the engineering core counts profiles across go-to-market, community, product, compliance, design and strategy. We operate as an autonomous product team and share an entrepreneurial mindset and a firm belief that we can cover new grounds to the benefit of the world. We work with trust, collaboration and flexibility as our foundations.What we offerOpportunities for professional growth and development.A supportive company culture and inclusive workplace environment.Daily meals, snacks, and beverages in our canteen.Office amenities such as company bikes, a gym, massages, and Friday gatherings.Monthly company events for team bonding and enjoyment.Apply NowWe would like to receive your pictureless CV in English; a short custom summary may be integrated into your resume. If you have any questions, you are very welcome to contact Fulgencio Navarro Senior Platform Engineering Manager Phone: +34 662 024 273We would like you to start as soon as possible, and we will hire on an ongoing basis as we interview candidates.Join us in shaping the future of computer vision through engineering and innovation. Lets build products, services and your career in a meaningful way together!About usHafnia is a team within Milestone, an international company with development sites in Denmark, Bulgaria, Spain and offices all over the world. We are technology driven as we are developing and maintaining one of the most advanced video management software in the world. Innovation is not only important for us. It is a part of our DNA just as responsible use of technology which we actively support. We believe in trust, mutual respect, a healthy work life balance and room for all voices to be acknowledged. As such, we expect you to engage, speak up, and make a difference for your team, our customers, and yourself. Read more at www.milestonesys.com or hafnia.milestonesys.com for Hafnia specific information.