Experience Senior · 6+ yrs (1+ years)
About the role
structured by ORICekuraVoice AI and Chat AI agents: Testing and ObservabilityMember of Technical Staff, Cekura (San Francisco, In-Person)$150K - $200K•0.20% - 0.80%•San Francisco, CA, USJob typeFull-timeRoleEngineering, Full stackExperienceAny (new grads ok)VisaWill sponsorConnect directly with founders of the best YC-funded…
What you will do
- Build the testing and simulation engine that simulates thousands of realistic conversations against customer agents across voice, chat, and phone.
- Push the frontier of agent evaluation by building LLM-powered evaluators, metrics, and the closed self-improvement loop.
- Do applied audio and speech research to map the paralinguistic layer of conversation into structured signals.
- Own real-time voice infrastructure including SIP, WebRTC, WebSockets, STT/TTS pipelines, and providers like Twilio, Vapi, Retell, LiveKit, and Pipecat.
- Ship end-to-end features from design to production across backend, infra, evals, and the product surface.
What they are looking for
- Strong coding ability in Python, TypeScript, or Go.
- Experience with at least one of: distributed systems, real-time infrastructure, or LLM-based products.
- Strong written and verbal communication.
- Work in-person in San Francisco.
Nice to have
- Hands-on experience with LLM evals, agent frameworks, or AI observability.
- Voice AI experience: Twilio, SIP, WebRTC, Vapi, Retell, LiveKit, Pipecat, or STT/TTS pipelines.
- Early-stage startup experience, or early engineer at a dev-tool, infra, or AI company.
- Open-source contributions or public technical work.
- Ex-founder or aspire to be one.
Before you apply
- In-person in San Francisco, six days a week, long days, most weekends.
Benefits
- Top-of-market cash
- Meaningful equity
- Medical, dental, vision
- Daily lunches and dinners
- Relocation support to live near the office
PythonTypeScriptGoLLMsSIPWebRTCWebSocketsNLPTwilioVapiRetellLiveKitPipecatElevenLabs
Full posting text
Experience: 1+ years