Location: Tel Aviv
#Hybrid
DriveNets is a leader in high-scale disaggregated networking solutions. Founded in 2015, DriveNets modernizes the way service providers, cloud providers and hyperscalers build networks. Supporting the largest network in the world, more than half of AT&T’s backbone traffic is running on DriveNets’ Network Cloud open disaggregated architecture. Raising $587 million in three funding rounds, DriveNets is disrupting the networking market from high-scale architecture to AI platforms, and is bringing onboard the most talented people. We are seeking people that want to make an impact on the world’s leading communication networks and are experienced in networking architecture or AI infrastructure solutions.
Job Summary
We are seeking a skilled software engineer to join our NPU software stack development team. This role involves developing high-performance GPU programming frameworks, runtime systems, and libraries for AI/ML workloads. You will be responsible for implementing, optimizing, and maintaining GPU software stack components to support distributed AI training and inference.
Key Responsibilities
- Identify bottlenecks, analysis and optimize in distributed NPU eco-system
- Design and develop NPU memory management system
- Design and develop optimized NPU development framework, execution path and debugging
- Develop compatibility with AI frameworks (Triton, PyTorch, JAX)
- Write high-quality, well-tested code with comprehensive documentation
- Collaborate with other teams (Hardware, Network, QA, AI Framework Integration)
- Participate in code reviews and technical design discussions
Requirements
Required Qualifications
- 5+ years of experience in distributed system programming
- 3+ years of experience with NPU programming (Triton, CUDA, HIP, OpenCL)
- Expert-level C/C++ programming with focus on performance optimization
- Expert-level Python programming with focus on DL/ML frameworks (PyTorch/JAX/etc)
- Deep understanding of NPU architecture, memory tiering, and programming models
- Knowledge of NPU runtime systems
- Experience with performance profiling and optimization tools
- Strong problem-solving and debugging skills
- Experience with version control systems, Ticking system and collaborative development
- Team player with excellent communication skills
- Fast learner, highly organized, detail-oriented with high motivation
Preferred Qualifications
- Experience with NPU software stack development
- Experience with large-scale NPU systems (100+ NPUs)
- Experience with DL/ML workloads (oriented AI) and distributed training / inferencing
- Familiarity with containerization and orchestration
Skills Required
- 5+ years of experience in distributed system programming
- 3+ years of experience with NPU programming (Triton, CUDA, HIP, OpenCL)
- Expert-level C/C++ programming with focus on performance optimization
- Expert-level Python programming with focus on DL/ML frameworks (PyTorch/JAX/etc)
- Deep understanding of NPU architecture, memory tiering, and programming models
- Knowledge of NPU runtime systems
- Experience with performance profiling and optimization tools
- Strong problem-solving and debugging skills
- Experience with version control systems and collaborative development workflows
- Excellent communication and teamwork skills
- Fast learner, highly organized, detail-oriented and motivated
- Experience with NPU software stack development
- Experience with large-scale NPU systems (100+ NPUs)
- Experience with DL/ML workloads and distributed training/inferencing
- Familiarity with containerization and orchestration
What We Do
DriveNets is a rapidly growing software company that has created a radical new way for service providers and hyperscalers to build their networking infrastructure. DriveNets Network Cloud and DriveNets Network Cloud-AI are new innovative networking solutions that apply the cloud architectural approach to high-scale networking. They bring together the scalability of standard Ethernet Clos architecture with the high performance and reliability of service provider networking, delivering optimal networking performance, scale and cost structure for service providers and hyperscalers. Founded by Ido Susan and Hillel Kobrinsky, two successful telco entrepreneurs, DriveNets Network Cloud is the leading open disaggregated networking solution based on cloud-native software running over standard white boxes. Over three funding rounds, DriveNets raised $587 million. Its solutions are used by tens of service providers globally and are in proof-of-concept and lab trials at dozens of operators and hyperscalers, consistently ranking #1 in trials for breadth of capabilities and solution quality. AT&T, the largest backbone in the US, deployed DriveNets Network Cloud across its core network, and DriveNets is currently transporting more than 52% of AT&T’s core network traffic. DriveNets is engaged with over 100 Tier-1 operators and cloud-providers on large projects in North America, Asia and Europe.
