We are FastCTO (fastcto.com) - we're not a dev shop or outstaffing company.

We have a unique and interesting model where we help startups by matching them with really fancy CTOs and then build a dev team - sometimes with internal developers, sometimes with Upwork or somewhere else - but always only senior developers.

Every company is a little different - different stacks, different environments, sizes, etc but every company is a long-term, fun engagement with awesome culture, smart people, and good code.

Right now, we have an opening for а Senior Voice AI Engineer or with strong experience in integrating TTS/STT systems (ElevenLabs, OpenAI, Vapi, etc.) and building low-latency, real-time voice applications.

Key responsibilities

• Design and implement the architecture for a low-latency voice-first MVP.
• Integrate and optimize TTS/STT endpoints.
• Reduce token usage and optimize turn-by-turn performance (prompt refactoring, RAG, embeddings).
• Implement session and persistent memory + extraction of key user variables (age, names, marital status, fears, etc.).
• Ensure performance and latency remain equal or better than current solutions.
• Recommend the best voice approach, tech stack, and architecture.
• Deliver a working prototype with documentation and a scalable plan.

If it sounds interesting to proceed - please apply and let's chat!