About the role
What we're looking for:
We need a Staff/Principal-level backend engineer with 8+ years of experience building and deploying cloud-based services at scale who thrives in a fast-moving startup environment. You should be comfortable working as a strong IC with technical autonomy, have a track record of shipping zero-to-one platform products, and bring adaptability across tools and programming languages. Bonus points if you have experience with AI products, founder experience, or have worked at high-caliber companies like Databricks or similar AI/infrastructure startups.
What you'll do:
- Own core backend systems for Inworld Router — an intelligent routing layer across 200+ LLMs with multi-provider failover, cost/latency-based routing, and real-time observability at massive scale
- Build and scale API-based model services (TTS, STT, LLM, Knowledge/RAG) powering consumer-facing AI applications with hundreds of millions of end users
- Design and implement realtime, low-latency systems for speech-to-speech and Realtime API products
- Collaborate closely with PMs, engineers, and sibling ML teams to determine the biggest product needs and ship quickly in a rapidly evolving AI landscape
- Drive system improvements and advocate for new technical standards, dependencies, and architectural decisions with considerable technical autonomy
- Work on ambitious new products launching later this year, including platformization of new offerings and system-wide infrastructure projects
Key context:
- This is a pure IC role — no management responsibilities, but strong ownership expected
- Flat team structure reporting to the VP of Engineering (~7-8 person team)
- AI tools and agents are embraced in the development workflow and interview process
- Startup experience is strongly preferred — candidates from only large tech companies without any startup background are not a fit
