5 months ago
Gdańsk, PolandStaff+
Responsibilities
- Design, implement, test, and document the Collectives Communication Library for new AI hardware accelerators
- Collaborate with other teams to design, implement, and test new features
- Troubleshoot and resolve complex technical issues
- Ensure seamless integration of new hardware with the existing AI ecosystem
- Lead development efforts, mentor junior engineers, and drive technical excellence
- Work as part of an agile scrum team
Requirements
- Extensive software development experience using C++
- Experience with Python and C
- Strong problem-solving, debugging, and complex issue-resolution skills
- Strong knowledge of multithreading and inter-process communication techniques
- Experience with unit testing frameworks such as Boost.Test and Google Test
- Proficiency with CMake, Make, and Ninja
- Strong understanding of version control systems, preferably Git
- Ability to work with multinational teams and customers
- Excellent written and verbal communication skills
- Experience with RDMA networking libraries such as libibverbs or libfabric is desirable
- Knowledge of multithreading, parallel computing, parallel algorithms, and optimization for AI/ML and HPC systems is desirable
- Experience with CI/CD pipelines and automated workflows and deployments such as GitHub Actions or GitLab CI is desirable
- Experience with communication libraries such as NCCL or MPI is desirable
- Knowledge of machine learning frameworks such as PyTorch is desirable
- Knowledge of modern C++ standards 17/20 is desirable
Benefits
- Annual leave policy
- Medical and dental health plans
- Gym card
- Employee pension matched up to 4%
- Flexible interview approach and reasonable adjustments
- Inclusive and equal-opportunity work environment
About Graphcore
Graphcore designs and sells Intelligence Processing Units (IPUs), systems, and a full software stack for training and inference of AI models in data centers and research labs. Revenue comes from hardware systems and associated software tools and services, used for workloads across NLP, computer vision, and graph neural networks. Founded in 2016 and headquartered in Bristol, the company is part of SoftBank Group and focuses on on‑prem and cloud deployments.