Model Evaluation QA Lead

Deepgram(5 days ago)

RemoteFull TimeSenior$180,000 - $230,000Engineering

About this role

Deepgram is seeking a Model Evaluation QA Lead to oversee model quality assurance in their AI pipeline, focusing on speech-to-text, text-to-speech, and voice agent evaluation. The role involves building automated evaluation frameworks, integrating quality gates into deployment pipelines, and ensuring high standards across multiple languages and domains. This position plays a critical part in maintaining Deepgram's leadership in voice AI quality.

View Original Listing

Required Skills

Python
ML Evaluation
Data Processing
Speech Recognition
Evaluation Metrics
CI/CD
Benchmarking
Audio Processing
Model Validation
Evaluation Frameworks

About Deepgram

www.deepgram.com

Deepgram is an advanced voice technology company that specializes in providing enterprise solutions through its Speech-to-Text (STT), Text-to-Speech (TTS), and Voice Agent APIs. Its platform offers real-time, highly accurate transcription and voice synthesis capabilities, designed to scale with the needs of businesses. Deepgram's solutions are built for integration into various applications, enabling companies to leverage sophisticated voice AI technology for enhanced customer interactions and operational efficiency.

View more jobs at Deepgram →