About the role
The team manages Luma's model serving infrastructure. The engineer integrates new model architectures, scales deployments across numerous machines, and optimizes the use of GPU resources. This involves building tools for monitoring, automating, and maintaining the reliability of inference services.
Our summary of the posting; the original is on the Luma AI careers page.
What the posting requires
- Required
- Python
- PyTorch
- Queues
- Linux
- Redis
- System architecture
- Hugging Face
- Scheduling
- Docker
- S3
- Preferred
- Networking
- ML systems
- CUDA
- RDMA
- Gpu
- FFmpeg
These tags are our reading of the posting. They can miss something; the original posting is the reference.