1 day ago
Helsinki, FinlandStaff+
Responsibilities
- Design and lead a secure internal LLM serving platform on fully controlled GPU hardware.
- Manage GPU clusters, inference engines, access control, capacity planning, and the full serving stack.
- Establish platform standards and ensure compliance with regulatory frameworks such as DORA.
- Partner with security, operations, and LLM scientists to deploy optimized models.
- Write architecture guidelines and collaborate with enterprise architecture teams.
Requirements
- Experience designing and running large-scale infrastructure on Kubernetes, including GPU workloads.
- Hands-on experience with LLM inference engines such as vLLM, SGLang, or TensorRT-LLM.
- Experience with infrastructure as code, CI/CD, and observability tooling.
- Understanding of security, identity, and network design in enterprise environments.
- Experience writing architecture guidelines and working with enterprise architecture teams.
- Experience configuring and managing NVIDIA or AMD Instinct GPUs and CUDA or ROCm is preferred but not required.
- Background in banking or other highly regulated industries and familiarity with DORA or equivalent compliance frameworks is preferred but not required.
Tech Stack
Categories
About Qutwo
Qutwo builds enterprise AI and quantum-computing solutions, combining its Qutwo OS, ML pipelines for neural network compression, and security-focused SaaS services for industrial optimization, simulation, and analytics. The company partners with enterprises to develop classical, hybrid, and quantum systems and offers software plus applied research engagements. It is privately held, Europe-based, and was co-founded by pioneers behind IQM and Silo AI, with backing from founders of Skype, Hugging Face, Quantinuum, and Supercell.