Medior GPGPU engineer - CUDA HIP SYCL OpenCL

Amsterdam, Netherlands | Posted on 06/03/2024

Note that this is a software development role, not a testing role. No mention of any GPU-related skill = immediate rejection, which is over 80% of the applicants. Please, please, please spend some time to update your CV, and know you can list university-projects and hobby-projects.

We’re playfully serious. We handle serious problems, but we’re all active gamers. We have an art to balance between tinkering and making progress.

Our job is "simply" building extremely fast software using the latest hardware (both GPUs and CPUs) and the most efficient HPC and GPGPU tech (CUDA, HIP, SYCL, OpenCL, MP, MPI). Besides technical skills, this takes good project management, putting most time to problem-solving and having superb understanding of how code and data stream through the CPUs and GPUs.

For over 10 years we’ve been called on by companies worldwide to solve their HPC- and GPU-problems. We seek people who’d like to strengthen our group of GPU- and HPC-enthusiasts.

We have offices in Budapest, Barcelona, and Amsterdam, and work hybrid with 3 days in the office.

ABOUT US, as your team and your employer

Stream

HPC is a self-funded company with enough cash reserves and customers to provide stable jobs. This explains why we seek people who want to work for us for the long term.

We’re different from most development companies, and not just in the type of work we do.

We invest in our people. We have a 4 month onboarding period, create personal development plans and coach each other. We allocate time & provide guidance in setting goals. You earn trust by accomplishing those goals. By understanding what is blocking somebody (skills, attitude, experience, etc), we help each other to improve. As we’re not a large corporation, we seek people who already have the right attitude for such personal and professional growth.

We do more than just coding. We are still a relatively small company, and our engineers have a say in every part of the company to improve it for the long term. This means they commit time to things that are not coding.

We like to solve problems as a team, as individuals we then don’t need to be strong in all areas. For us, teamwork is having conversations about what is working, what isn’t and what to do about it. It means following up and making things happen. Occasionally it means talking about feelings, or sharing struggles dealing with Asperger's or ADHD - all to make sure you can advance your chosen career path.

We value openness to new experiences, to people, to feedback, and especially to learning. Particularly in areas where doing so is uncomfortable. How comfortable are you dealing with the unknown?

And we do actual work most of the time. We make scientific software that performs. We are specialists in performance-driven software designs, GPUs, and high-end CPUs. Our clients come to us when they have a scientific computing problem to solve, build GPU-software or to build complex tools. Our initial effort focuses on understanding their needs, provide clarity on potential solution paths, and work with the customer to deliver the right solution.

We then build. Every project is different.

APPLICATION PROCESS

If you respond quickly for every step, you can land a job in 2 weeks.

We try to minimize the time it takes you, while also giving you enough chances to prove yourself. As we are sometimes flooded with applications, we filter out on simple things like “Did not mention CUDA, OpenCL, SYCL, GLSL, HLSL, etc” – be sure you add GPU-experience!