HPC is an important and technically challenging compute domain, with specialised tooling and a very high requirement for precision, efficiency and automation.
This role covers engineering management of a software development team we have created to deliver an outstanding HPC experience - from bare metal to public cloud - as part of the broader Ubuntu platform.
We are looking for a range of skills and experience, but the heart of our effort will be Python software development for automation of key software in the HPC sphere.
As an engineering manager, you must also have excellent judgement about people - their motivations, abilities, developmental needs and prospects for success.
Engineering at Canonical requires hands-on code contribution and review, as well as architectural leadership.
You will need to demonstrate insight into performance and quality engineering practices and ensure your team embraces effective disciplines on both fronts.
You will need to be comfortable holding contributors accountable for work ethic and results.
You must also have an understanding of security practices and principles and the impact that engineering choices have on product security.
We expect teams to deliver well-documented products and work with design professionals to shape the product experience.
You should relish the opportunity to shape and direct and develop an engineering team that is happy and brilliant, and produces a product that will be a pleasure to use and to evolve.
For this role you must have deep experience with Python.
Experience in HPC environments is a strong advantage.
Familiarity with HPC hardware and software is also a strong advantage - delivering great experiences with Infiniband, RDMA, CUDA, MPI, Slurm, Lustre, Singularity and related technologies will be central to this team's work.
It will also be advantageous to have experience with Docker image design and operations, and public cloud image design and operations.
stack
LI-remote