CareerPlan

Member of Technical Staff (Speech)

San Francisco (On-site)Full-time2026-07-29 → 2026-11-18
On-site

Core

Build and extend speech evaluation frameworks, benchmarks, and arenas (e.g., AgentTalk) to measure and analyze the performance of text-to-speech, speech-to-text, and speech-to-speech models.

Role type

Senior IC speech AI benchmarking engineer

Builds

Speech benchmarking platform, leaderboards, and analysis reports

Domain

AI / Speech Technology

Deliverable

production ML models

Required skills

Python, data analysis, speech AI model evaluation, quality assessment, word error rate measurement, latency measurement, preference testing, prompt engineering

Preferred skills

Experience at speech AI companies (e.g., ElevenLabs, Cartesia), experience at large platform voice teams, knowledge of frontier AI

Technologies

Python, modern speech models

Responsibilities

Benchmark new speech models and providers as they launch, design evaluation frameworks and prompt libraries, partner with leading speech AI companies, publish leaderboards and analysis, shape the product roadmap

Seniority

Senior, hands-on IC