About the role
Responsibilities:
- Own the end-to-end system from camera to customer, including real-time video ingestion from factory floors with unreliable networks.
- Build and scale GPU inference systems for real-time workloads.
- Develop stream recovery and autoscaling mechanisms.
- Drive cost optimization and ensure high reliability of customer-facing live systems.
- Own production performance and reliability under scale and operational pressure.
Requirements:
- Proven experience scaling complex real-time systems by an order of magnitude in production.
- Strong systems thinking and first-principles problem-solving skills.
- Experience working with hard latency requirements, backpressure, and failover.
- Experience in video is not required; relevant experience in voice, streaming, trading, telemetry, or other real-time systems is valuable.
- Ability to work effectively in unfamiliar and technically challenging domains.