About this role
Role Overview
- Design and iterate on "post-processing" test suites and automated evaluation platforms for multilingual, multi-model online systems, covering hallucinations, casing, formatting (numbers/punctuation), and segmentation (chunking/forced breaks).
- Establish specialized evaluation benchmarks for LiveAgent systems, focusing on VAD false triggers, interruption latency, and turn-taking transitions.
- Resolve "high-friction" issues—such as hallucinations, casing inconsistencies, and poor segmentation—that negatively impact user experience, achieving SOTA precision on par with industry leaders.
- Optimize VAD, barge-in (interruption) models, and turn-taking strategies to minimize end-to-end latency and False Interruption Rates, benchmarking against top-tier global voice assistants.
Requirements
- 1–3 years of hands-on experience in speech algorithm training with a focus on speech pre/post-processing or the optimization of Full-Duplex voice interaction systems.
- Proven experience in ASR pre-processing (e.g., VAD, denoising) or post-processing (e.g., ITN, punctuation, text normalization).
- A track record of publishing at top-tier speech conferences (e.g., Interspeech, ICASSP) or a portfolio of speech-related invention patents.
Benefits
- Top-tier healthcare for employees and dependents, including dental and vision, and a generous employer subsidy.
- 401(k) plan for full time employees with company matching.
- Unlimited PTO, plus 13 paid holidays.
- 12 weeks of paid time off to spend time with your new family, regardless of gender.
- Minimum of 3x in office per week.
- New hires are equipped with their choice of new top-of-the-line laptops and workstation setups.
- Best office equipment. Annual offsites. Free office drinks and snacks.