About the job
The job is about owning the model inference stack at Coreflow, a fast-growing startup redefining entertainment with AI. This opportunity allows you to serve in-house and open-source models to tens of millions of users while ensuring low latency and high throughput. The team values a user-first approach, high agency, and urgency, creating an inspiring environment for innovation and performance.
You'll be responsible for
📦
Owning model inference stack
Managing the end-to-end process of serving in-house and open-source models to users.⚡
Optimizing performance
Squeezing every bit of performance out of the GPU fleet to ensure high throughput.🤝
Collaborating with teams
Working closely with cross-functional teams to align on user needs and project goals.Key criteria
⚙️
Model inference stack ownership
Experience owning model inference stacks for high-performance applications.View
🚀
High throughput experience
Demonstrated experience achieving high throughput in server environments.View
💻
GPU performance optimization
Proven skills in optimizing GPU performance for scalable applications.View
