Responsibilities and Opportunities

• Designing an RBLN runtime module that interfaces RBLN compiler and driver modules
• Designing and implementing user-level APIs, adding support for various language bindings, deploying ML models to the RBLN SDK, and maintaining user documentation
• Conducting benchmarking and profiling to evaluate the existing runtime system's performance and implementing optimizations to enhance the overall system performance of RBLN NPU products
• Optimizing inference serving using vLLM for NPU and conducting SOTA (State-of-the-Art) research to improve model serving performance

Key Qualifications

• Bachelor's or higher degree in Computer Science, Electrical Engineering, or a related field
• Comprehensive understanding of deep learning models and their applications in vision, natural language processing, speech recognition, and other domains
• Familiarity with system software, including compilers, runtimes, drivers, firmware, etc.
• Proficiency in programming languages: C++ and Python
• Knowledge of data structures, algorithms, and OOP design patterns
• Strong written and verbal communication skills

Ideal Qualifications

• Hands-on experience with AI accelerator (e.g., GPU) driver APIs and runtimes
• Exposure to ML frameworks such as PyTorch, TensorFlow, ONNXRuntime, TensorRT, and their respective optimization techniques
• Solid understanding of operating systems, resource management, and high-performance computing principles
• Deep expertise in Python or modern C++ and its advanced features for writing efficient, high-performance code
• Experience with multithreading and parallel programming
• Experience with serving platforms such as vLLM, TorchServe, and Triton Inference Server