AI Engineer, Voice and Realtime
ObbleAbout the role
Obble screens and interviews candidates over a live call. That means audio in, transcription, a model deciding what to ask next, and speech back out, inside the pause a person will tolerate before it feels broken.
This role owns that pipeline: the realtime worker, the prompts, the vendor seams behind them, and the evaluation harness that tells us whether a change made the interviewer better or only different.
What you will do
Own the realtime interview worker: audio handling, speech-to-text, model calls, and turn-taking under a latency budget.
Design prompts as engineering artifacts, versioned and measured against a frozen corpus rather than adjusted by vibes.
Run the evaluation loop: build the scenarios, read the transcripts, and defend a change with numbers before it goes live.
Keep the vendor layer swappable. Models and speech providers change; the product should not have to.
What we are looking for
Strong Python, and experience shipping something that called a language model in production rather than in a notebook.
Comfort with asynchronous and streaming code, and the debugging that comes with it.
A measurement instinct: when a model output is wrong, your first move is to build the case that proves it.
Care about the person on the other end of the call. A candidate is being interviewed by this system, and that deserves real thought.
Nice to have
WebRTC, LiveKit, or any realtime audio stack.
You have run evaluations or A/B comparisons on model output before.
Apply for this role
Four fields and a resume. No account, no portal, no eleven-step form.
Your name(required)Email(required)LinkedInOptionalPortfolio or GitHubOptional
Resume
Responsibilities
- Own the realtime interview worker: audio handling, speech-to-text, model calls, and turn-taking under a latency budget.
- Design prompts as engineering artifacts, versioned and measured against a frozen corpus.
- Run the evaluation loop: build scenarios, read transcripts, and defend changes with data.
- Keep the vendor layer swappable for models and speech providers.
Qualifications
- Strong Python skills and experience with language models in production.
- Comfort with asynchronous and streaming code.
- Measurement instinct for model output evaluation.
- Consideration for the candidate experience during interviews.
Skills mentioned
About Obble
Hiring is changing faster than ever we could have imagined. But the way people discover, evaluate, and trust talent hasn't kept up. We're building something ambitious to change that. Obble is creating a new foundation for modern hiring, designed to remove friction, improve confidence, and help great decisions happen faster. We're still in stealth, working closely with early partners and refining every detail before launch. More soon!