Company : Argo AI GmbH
Who we are :
Argo AI is in the business of building self-driving technology you can trust. With experienced leaders in the field and collaborative partnerships with some of the world’s largest automakers, we’re building self-driving technology that is engineered to scale globally and transform mobility for millions.
Talented individuals join our team because they share our purpose to make it safe, easy, and enjoyable for everyone to get around cities.
We aspire to impact key industries that move people and goods, from ride hailing to deliveries.
Meet the team :
Our System Performance Accelerator (SPA) team designs and implements High Performance Computing (HPC) libraries, with an edge towards GPU Computing.
We pair our efforts with HPC training & cross-functional hands-on helping autonomy teams to deliver algorithms for controlling the vehicle’s movement.
We use the latest hardware with multi-core CPUs & many-core GPUs with the latest software toolchains to achieve our goals.
Key technologies / compilers used are : C / C++14 / 17, multi-threading, CUDA, bazel, nvcc, gcc, clang on unix platforms.
We aim for the safest and most performant way to deliver our libraries, while keeping key ease-of-use & re-usable library code for our autonomy team clients.
What you’ll do :
Analyzing the architecture & designs of existing HPC / GPU libraries & solutions and propose new ideas, approaches and implement them
Work cross-functionally & hands-on with our autonomy team clients, training & helping them using HPC / GPU methodologies
Optimize implementations in respect to efficient use of the parallel computing hardware
Contributing to the built up of the infrastructure / processes / standards in the team
Work as a member of either SPA or OLA sister teams, depending on location (EU / US)
Producing high quality software in the safety relevant context of fully automated driving
What you'll need to succeed :
Degree in Computer Engineering, Computer Science, Electrical Engineering, Robotics or a related field
Excellent programming skills in C / C++ (C++14 / 17)
Multiple years of hands-on experience with GPU Computing (APIs like CUDA, OpenCL, OpenGL / GLSL / Compute Shaders,
Vulkan / SPIR-V)
Hands-on experience in developing multi-threaded applications in C / C++
Good understanding of library architecture, design and implementation
Good foundation of applied computer science and object oriented (OO) design
Good understanding of operating system architecture and systems programming
Passionate for producing high-quality, production-ready and well-tested code
Masters Degree or PhD on HPC subjects
Nice to haves :
Many years of experience in GPU Computing; library development is a plus
CUDA as a GPU Computing API focus
Practical experience in embedded and real-time automotive platforms
Knowledge about build systems and development environments (bazel, cmake)
Experience with scripting languages such as Python is a plus
What we offer you :
Competitive compensation packages
30 vacation days
Subsidized daily lunches, beverages, and snacks
Professional development reimbursement
Global Employee assistance program (Offerings include : work-life balance support, mindfulness programs, life coaching, new parent coaching, and more!)
Local and global discount programs
Company and team bonding outlets : employee resource groups, quarterly team activity stipend, and wellness initiatives