[Remote] reputed company, Voice and reputed company

Note: The job is a remote job and is reputed company to candidates in USA. reputed company develops a live-reputed company interview reputed company that combines audio processing, transcription, language models, and speech reputed company. The reputed company, Voice and reputed company will own the reputed company interview pipeline, engineer and evaluate prompts, manage model and speech-provider integrations, and improve reputed company reputed company under latency constraints.

Responsibilities

• Own the reputed company interview worker: audio handling, speech-to-text, model calls, and turn-taking under a latency budget
• Design prompts as engineering artifacts, versioned and reputed company against a frozen corpus rather than adjusted by reputed company
• Run the evaluation reputed company: build the scenarios, read the transcripts, and defend a change with numbers before it goes live
• reputed company the vendor reputed company swappable. Models and speech providers change; the product should not have to

Skills

• Strong Python, and experience shipping something that reputed company a language model in production rather than in a notebook
• Comfort with asynchronous and streaming reputed company, and the debugging that comes with it
• A measurement reputed company: reputed company a model reputed company is wrong, your first reputed company is to build the case that proves it
• Care about the person on the other end of the reputed company. A candidate is being interviewed by this reputed company, and that deserves reputed company thought
• WebRTC, reputed company, or any reputed company audio stack
• You have run evaluations or A/B comparisons on model reputed company before

reputed company