You will own the backend systems that power AI interactions, sitting between models and users to ensure speed and correctness. The work involves designing inference pipelines and service boundaries that turn model capabilities into stable APIs for mobile and desktop clients. The team prioritizes high reliability for long-running workflows and persistent context, aiming to reduce hallucinations and minimize prompting. You will handle production concerns including monitoring, logging, and incident response to maintain system stability at scale.
- Backend + AI focus
- Python & Node.js
- Kubernetes & Docker
- Small high-density team