Research Engineer, Evaluations

AssemblyAI is seeking a Research Engineer to join our streaming speech-to-text research team. This role is pivotal in evaluating and benchmarking our voice AI models, ensuring they meet the highest standards of accuracy and performance. As part of a dynamic and rapidly growing company, you'll have the opportunity to influence the future of voice AI technology.

In this position, you will be responsible for designing and implementing evaluation frameworks, conducting competitive benchmarking, and translating customer feedback into quantifiable research objectives. Your day-to-day tasks will include managing evaluation datasets, developing metrics that reflect real-world performance, and collaborating closely with research and engineering teams to enhance our models.

The ideal candidate will possess a strong background in machine learning or research engineering, with proficiency in Python and experience with data pipelines and cloud infrastructure. A deep understanding of evaluation metrics, statistical rigor, and familiarity with voice agent systems are essential. Excellent communication skills and an ownership mindset are also critical for success in this role.

AssemblyAI offers a competitive salary range of $210,000 to $260,000, along with comprehensive benefits. As a remote-friendly company, we provide flexibility and support for our team members to thrive in their roles.

Joining AssemblyAI means becoming part of a meritocratic environment where innovation and impact are valued. With a lean team structure, you'll have significant ownership and the chance to work on cutting-edge problems in the voice AI space.