At Telenor AI Factory, we are not just building infrastructure, we are building the future of AI in Norway. As a fully Norwegian-owned initiative, we are scaling fast, driven by real customer demand and feedback. Our mission is clear: deliver what our customers need, when they need it, with sovereignty, security, sustainability and innovation at the core.

Backed by strategic partnerships with NVIDIA and other global tech leaders, we have created Norway’s first sovereign, secure, and sustainable AI cloud service, designed to accelerate AI adoption across industries.

We are now entering a new phase of growth, expanding into a new data center and scaling our services to meet increasing demand. If you are passionate about AI, customer-centric innovation, and being part of something truly transformative and pioneering, this is your chance to be part of shaping Norway’s AI future.

As we continue to scale our business, we are seeking an entrepreneurial-minded lead for our AI Services team. This is a hands-on role that combines deep technical expertise in AI inference and model operations with technical leadership. You will write code, own the architecture, and lead a team of engineers by working alongside them. You will be key in shaping, developing and operating the AI services we deliver on our sovereign AI Factory, including our Model as a Service offering

Key responsibilities:

• Design, build and operate the model serving stack behind our Model as a Service offering

• Lead the DevSecOps AI Services team, setting the technical direction through architecture, code review and mentoring

• Evaluate, deploy, optimize, upgrade and operate large language models and other AI models, and own the lifecycle around them

• Own the benchmarking and evaluation discipline: model quality, latency, throughput, concurrency, GPU utilisation and memory consumption

• Own the capacity and cost model that determines the basis for AI service pricing

• Expose services securely through APIs and gateways, with authentication, authorisation, rate limiting, quotas and usage metering

• Own service quality process in production, including monitoring, service-level indicators, incident response, change request and continuous improvement

• Collaborate closely with the Cloud Infrastructure team, and with tech and business development, to align roadmaps and embed security and sovereignty into the services

Who are we looking for?

• Solid hands-on experience within AI engineering, MLOps, DevOps or platform engineering, running AI models in production

• Deep understanding of AI inference internals: tokenization, context length, KV cache and paged attention, prefix caching, continuous batching and chunked prefill, quantization formats

• Familiarity with strategies for scaling inference, such as prefill/decode disaggregation, tensor and pipeline parallelism, and speculative decoding

• Understanding of APIs, AI gateways, authentication, observability and production service operations, including semantic routing across models

• Hands-on experience with inference and serving stacks such as vLLM, SGLang, TensorRT-LLM, NVIDIA NIM or Dynamo

• Experience with model evaluation and benchmarking, and translating the results into capacity and cost calculations

• Understanding of AI security, including guardrails, prompt injection and jailbreak resistance, tenant isolation, and model supply chain integrity

• Experience with NVIDIA GPU-based infrastructure, including NVLink, NVSwitch, NCCL, InfiniBand, MIG and RDMA

• Strong architecture and technical skills in Kubernetes, ideally OpenShift

• Strong programming skills, preferably with Python

• Experience with cloud native operating models, including DevSecOps, GitOps, CI/CD and Infrastructure-as-Code

• Proven ability to lead engineers through technical direction and mentoring, in a hands-on capacity

• Familiarity with sovereign cloud principles and secure data residency

• Familiarity with Norwegian security act

• Familiarity with EU AI act

• Fluent in both Norwegian and English, with the ability to communicate effectively with a wide range of stakeholders

• Degree in Computer Science, Engineering, or a related field

We also believe you are:

• Innovative with agile mindset, motivated by solving complex challenges and prioritising business objectives.

• Collaborative and results-oriented, fostering cross-functional alignment.

• Embraces and fosters a culture of experimentation, learning, and collaboration.

• Strong communication skills to engage both technical and non-technical stakeholders.

What we offer:

• A unique opportunity to take part in the beginning of a new Telenor business venture, with a startup feeling and energy.

• Possibility to shape your own role and contribute with your ideas for development in the area.

• Part of a strong technology and security community in Telenor Group.

• Work with a fantastic team of engaged and experienced people who collaborate closely and appreciate everyone's ideas and opinions - we are building Telenor AI Factory together!

• You will be part of Telenor’s competitive benefits plan including our insurance - and pension schemes, vacation, etc.

• Flexibility in our way of working.

Important information:

• Application deadline: 30.09.2026. We’ll be looking at all the applications on an ongoing basis.

• Workplace: Telenor Fornebu.

• Background checks through Semac will be conducted on relevant candidates.

• If you have any questions about the position, you can contact the Hiring Manager, Pål Grønsund at +4793856442 or Pal.Gronsund@telenor.com.

• The candidate needs to be able to obtain a security clearance in accordance with the Norwegian Security Act.
  

Telenor AI Factory, founded in 2024 and consisting of a growing team of six employees, is Norway’s first sovereign, secure and sustainable AI cloud platform, built to handle sensitive data. Fully Norwegian owned and operated, it is dedicated to delivering secure, efficient and scalable AI services driven by real customer demand and feedback.