Job Description

About the Role: We're seeking an experienced Runtime Engineer to develop and optimize software systems for our silicon platform. This role focuses on building efficient runtime systems that maximize chip performance while ensuring reliability and ease of use. Key Responsibilities: * Design and implement runtime systems for AI accelerator execution and memory management * Develop and optimize runtime libraries for high-performance tensor operations * Create efficient memory allocation and scheduling algorithms for ML workloads * Interface with hardware subsystems through PCIe interface for optimal data transfer * Build and maintain runtime profiling and debugging tools * Work closely with hardware team to optimize end-to-end performance * Document runtime architecture and implementation strategies * Perform thorough testing and performance analysis of runtime components Required Qualifications: * BTech/MTech in Computer Science or Electronics & Communication * 4+ years of experience in systems programming with C/C++ * Strong understanding of concurrent programming and multithreading * Proficiency with debugging and profiling tools (gdb, valgrind, WinDbg, address sanitizer) * Experience with performance optimization and low-level system interfaces * Knowledge of memory management and scheduling algorithms Nice To Have: * Experience with ML frameworks (TensorFlow, PyTorch) and their runtime systems * Understanding of AI/ML workload characteristics * Background in driver development or hardware interfaces What We Offer: * Opportunity to work on cutting-edge high performance compute hardware * Collaborative environment with global teams * Fast-paced and innovation-driven culture * Chance to shape the future of AI acceleration