Speaker Diarization AI Researcher

Company DescriptionChordy.ai transforms conversations into actionable, searchable memories. It captures spoken interactions and generates transcripts, summaries, decisions, and action items that are connected to people and topics, building context over time. This innovative platform allows users to retrieve key information using queries like What did we decide last time or What did I promise to access past decisions and commitments. Designed to enhance focus and productivity, Chordy.ai empowers users with precise reminders and tools for seamless follow-through.Role DescriptionThis is a full-time remote role for a Speaker Diarization AI Researcher. The researcher will focus on designing and implementing advanced algorithms for speaker identification and segmentation to improve the speaker diarization models. Day-to-day tasks include conducting research on state-of-the-art methods, developing and optimizing machine learning models, processing datasets, collaborating with cross-functional teams to integrate new techniques into the companys product offerings, and contributing to publications and presentations in the field of AI and machine learning.QualificationsExperience with machine learning and artificial intelligence, particularly in speaker diarization, natural language processing, and audio signal processingProficiency in Python and frameworks such as TensorFlow or PyTorchStrong knowledge of algorithms, statistical modeling, and data analysis techniquesPrior experience working with large-scale audio datasets and deep learning methodsExcellent problem-solving skills with the ability to work independently in a remote environmentProven ability to contribute to scientific publications or present at industry events is a plusEducational background in Computer Science, Electrical Engineering, Machine Learning, or a related fieldadvanced degrees (Masters or Ph.D.) preferred