View job listing
The ideal candidate is a strong IC with high technical autonomy, a track record of shipping zero-to-one platform products end-to-end, and the ability to adapt across tools and programming languages.
Startup or growth-stage experience is strongly preferred. AI product experience, founder experience, or experience at high-caliber AI/infrastructure companies such as Databricks is a plus.
Apply to Staff/Principal Engineer
About the Role
Inworld is looking for a Staff/Principal-level backend engineer with 8+ years of experience building and operating cloud-based services at scale.The ideal candidate is a strong IC with high technical autonomy, a track record of shipping zero-to-one platform products end-to-end, and the ability to adapt across tools and programming languages.
Startup or growth-stage experience is strongly preferred. AI product experience, founder experience, or experience at high-caliber AI/infrastructure companies such as Databricks is a plus.
What You'll Do
- Own core backend systems for an intelligent routing layer across 200+ LLMs with:
- Multi-provider failover
- Cost/latency-based routing
- Real-time observability at massive scale
- Build and scale API-based model services across TTS, STT, LLM, and Knowledge/RAG.
- Build infrastructure powering consumer-facing AI applications serving hundreds of millions of end users.
- Design and implement real-time, low-latency systems for speech-to-speech and Realtime API products.
- Collaborate closely with PMs, engineers, and ML teams to identify product needs and ship quickly.
- Drive system improvements and influence technical standards, dependencies, and architectural decisions.
- Work on ambitious new products and system-wide infrastructure projects.
Key Context
- Pure IC role — no management responsibilities, but significant ownership expected.
- Flat team structure reporting to the VP of Engineering.
- Immediate engineering team of approximately 7–8 people.
- AI tools and agents are embraced throughout the development and interview process.
- Startup experience is strongly preferred; candidates coming exclusively from large tech companies are not a fit.
- Adaptability across languages and technologies is valued more than deep specialization in a single language.
Tech Stack
Go, Python, C++, Rust, PostgreSQL, MySQL, Redis, Memcached, Apache Flink, Apache Beam, ClickHouse, OpenTelemetry, GCP, AWS, Azure, Kubernetes, gRPC.Candidate Requirements
Dealbreakers- Built and operated cloud-based services at high scale — hundreds+ QPS.
- Hands-on experience with caching technologies such as Redis/Memcached, pub/sub or queues, and data pipelines such as Flink or Beam.
- 8+ years of backend software engineering experience.
- At least one startup or growth-stage company in their background; not exclusively big tech.
- Has shipped zero-to-one platform or product builds end-to-end.
- Technical degree in CS, physics, math, engineering, or a similar STEM field.
- Strong cloud infrastructure experience across GCP, AWS, or Azure.
- Experience operating relational databases such as PostgreSQL or MySQL at scale.
- Experience building AI products or real-time consumer-facing systems.
- Experience building API gateways, routing/proxy layers, or multi-provider orchestration systems.
- AI product, founder, or high-caliber AI/infrastructure startup experience.