9 hours ago
Remote, CzechiaMid Level
Responsibilities
- Own Voice AI agent capabilities from problem discovery and experimentation through architecture, implementation, testing, deployment, and impact measurement.
- Improve conversational quality, including latency, turn-taking, barge-in, speech recognition, multilingual behavior, protocol adherence, and transfers.
- Design fail-safe behaviors, improve service resilience and observability, and respond to production incidents through mitigation and prevention.
- Build automated evaluations, call-replay tools, production metrics, and controlled traffic trials to identify regressions and improve model and system behavior.
- Work across Python backend services, AI model behavior, React/TypeScript interfaces, APIs, web applications, and cloud infrastructure.
- Use AI tools for coding, testing, call analysis, and incident triage while retaining ownership of architecture, safety boundaries, and production decisions.
- Participate in a weekly on-call rotation and travel 1–2 times per quarter for in-person team gatherings, mostly within Europe.
Requirements
- 2–3+ years of backend or full-stack engineering experience shipping production software end to end.
- Hands-on experience building AI/LLM applications and solid fundamentals in distributed systems, APIs, and operational reliability.
- Strong Python proficiency, including asynchronous programming, with the ability to work with TypeScript and React or learn them.
- Ability to evaluate nondeterministic AI behavior using datasets, automated metrics, qualitative call review, controlled experiments, and statistical reasoning.
- Product-minded problem-solving, ownership, clear communication, collaboration, and a bias for action appropriate for safety-sensitive systems.
- Real-time voice, streaming media, or conversational agent experience is a strong plus.
- Experience with AI-assisted coding and finding new ways to use AI to improve engineering work is expected.
Benefits
- Competitive salary, benefits, and equity participation.
- Flexible, dynamic startup work environment with a highly talented team.
- Remote work is indicated by the #LI-Remote designation.
- Travel 1–2 times per quarter for in-person team gatherings, mostly within Europe.
Tech Stack
Categories
About RapidSOS
RapidSOS builds an intelligent safety platform that routes rich data from connected devices, apps, and sensors to 911 centers, first responders, and enterprise security teams. The company offers software and APIs used by public safety agencies and technology partners to deliver precise location and incident details during emergencies. Founded in 2012 and headquartered in New York, it is privately held; its network serves 16,000+ first responder agencies and supports over 171 million emergencies each year.