Efficiently transform ideas and concepts into working prototypes and production-level code.
Conduct in-depth performance analysis and profiling, and identify performance bottlenecks.
Devise and implement novel strategies that exploit algorithm insights and hardware capabilities for enhanced efficiency and speed.
Optimize core AI/ML algorithms to enhance performance.
Stay at the forefront of software, hardware optimization, and AI advancements, utilizing this knowledge to spearhead continuous improvements.
Offer technical leadership and mentorship, elevating engineering practices and contributing to the development process.
Requirements & Skills:
Master’s degree (or equivalent experience) in Computer Science, Engineering, or a related field.
Must have over 5 years of experience in software engineering and product development. A minimum of 2 years of experience in optimizing AI models is strongly preferred.
Outstanding proficiency in C/C++, with hands-on experience developing high-performance systems. Familiarity with SIMD programming, assembly, intrinsic functions, AVX, or similar instruction sets is a strong plus.
A strong understanding of memory allocation, the memory hierarchy, and optimizing to make the best use of caches and memory layout on multi-core, multi-socket servers.
Expertise in common data structures and an understanding of CPU/GPU architectures are essential for developing optimized software.
A thorough grasp of system architecture, including hardware accelerators and advanced optimization techniques.
Experience working with LLMs and a strong understanding of transformer attention is strongly preferred.
Strong communication abilities, capable of simplifying complex technical details for diverse audiences.
Adaptable and quick to embrace new technologies and methods, thriving in a fast-paced and innovative environment.
