Applied Researcher – AI Model Inference & Optimization

The Applied Researcher in AI Model Inference & Optimization plays a pivotal role in advancing our organization's capabilities in artificial intelligence. This position is integral to developing cutting-edge AI models that optimize performance and ensure efficient inference processes across a variety of applications. By leveraging state-of-the-art machine learning techniques and analytics, the researcher will seek to push the boundaries of AI technology, ensuring our models not only meet current industry standards but exceed them. Collaboration with cross-functional teams will be essential, as the researcher translates complex research findings into actionable insights that directly impact product development and operational efficiency. The ideal candidate will have a keen interest in exploring new methods for improving model inference speeds and accuracy, driving innovation within our organization. A passion for the latest AI trends and the ability to communicate research findings to non-technical stakeholders will further highlight the importance of this role in fostering a culture of innovation and excellence.

We are looking for an Applied Researcher with 6+ years of experience to focus on optimizing foundation model inference across diverse hardware architectures (GPUs, TPUs, MPUs, CPUs, and mobile devices). The ideal candidate will conduct cutting-edge research, design inference workflows, and lead cross-platform implementation teams.

✅ Research & analyze model inference techniques and optimization strategies

✅ Study and summarize state-of-the-art research papers

✅ Design efficient inference pipelines for different hardware platforms

✅ Define resource structures & technical requirements

✅ Collaborate with system architects to deploy AI models effectively

✅ Lead a cross-platform team for implementation & validation