As a Member of Technical Staff, Kernel Engineering at Inferact, you are driving the future of AI inference by optimizing kernel performance, leveraging your expertise in Python, Scheduling, Profiling tools, Machine Learning, and GPU Architecture. This critical role entails collaborating with cross-functional teams to develop and implement high-performance kernel solutions, accelerating AI progress and making inference cheaper and faster. By joining Inferact, you are contributing to the company's mission to grow vLLM as the world's AI inference engine, sitting at the intersection of models and hardware. This position offers immense growth and advancement potential, as you work on cutting-edge technologies, develop innovative solutions, and shape the future of AI. With Inferact's strong foundation, founded by the creators and core maintainers of vLLM, you are part of a team that is pushing the boundaries of what is possible in AI.

As a Member of Technical Staff, Kernel Engineering, your key responsibilities include:

• Designing, developing, and optimizing kernel solutions to accelerate AI inference, utilizing expertise in GPU Architecture and Machine Learning


• Collaborating with the software engineering team to integrate kernel solutions with the overall vLLM architecture, ensuring seamless performance and efficiency


• Utilizing Profiling tools to analyze and optimize kernel performance, identifying areas for improvement and implementing data-driven solutions


• Developing and maintaining scheduling algorithms to optimize resource allocation, ensuring maximum throughput and minimal latency


• Working closely with the research team to stay up-to-date with the latest advancements in AI and kernel engineering, applying this knowledge to drive innovation and improvement


• Participating in code reviews and contributing to the development of best practices, ensuring the highest standards of quality and excellence


• Collaborating with the DevOps team to ensure smooth deployment and maintenance of kernel solutions, guaranteeing maximum uptime and reliability. As a technical expert, you are working closely with the engineering team, reporting to the Technical Lead, and contributing to the development of Inferact's technical roadmap. Your day-to-day activities involve