Aircall seeks a Machine Learning Engineer to build evaluation frameworks for AI agents across voice and chat products. You will design pipelines for evaluating TTS/ASR, analyze failure modes, and implement regression tests to ensure reliability as models evolve.
Collaboration with teams to establish metrics, datasets, and tooling for scalable, trustworthy evaluations. The role emphasizes hands-on model evaluation, data pipelines, and strong communication to explain complex concepts to
#J-18808-LjbffrML Engineer: Voice Models & Evaluation Architect in san francisco at Unknown Company
This position is listed as full time and onsite.