NPU Team Leader

A successful high-tech company that has developed a software solution enabling telecommunications providers to increase network capacity at significantly lower costs.

The company is a unicorn, having completed a major Series C round, and employs hundreds of people globally, with a substantial presence in Israel.

Based in Tel Aviv, near a train line, the company operates a hybrid work model with one day per week from home.

Role Overview:

This role involves leading a team of 3–4 engineers within the NPU Software Stack development group. The team is responsible for building and maintaining frameworks, runtime systems, and high-performance libraries that support distributed AI and ML workloads.

Key responsibilities include-

• Design, development, optimization, and maintenance of NPU software components
• Enabling efficient distributed training and inference of AI models
• Close collaboration with Hardware, Networking, QA, and AI Framework Integration teams
• Deep involvement in performance optimization, memory management, and execution path design
• Adapting runtime components to leading AI frameworks
• Core Technologies: C++, Python, Triton, CUDA, HIP, OpenCL, PyTorch, JAX, Distributed Systems, NPU Programming, Runtime Systems, Performance Profiling, HPC, AI Infrastructure

Requirements-

• BSc/MSc in computer science/computer engineering or equivalent
• 8+ years of experience in systems programming and distributed computing
• 5+ years of leadership experience managing technical teams
• Expert-level C/C++ programming with focus on performance optimization
• Experience with NPU programming (Triton / CUDA / HIP / OpenCL)
• Deep understanding of distributed systems, communication protocols, and network programming
• Experience with DL/ML frameworks (PyTorch, TensorFlow) and distributed training / inferencing
• Experience with performance profiling and optimization tools
• Strong communication and interpersonal skills