About the role
The team builds and maintains the systems that deploy trained AI models into production. The engineer in this role is responsible for the entire inference pipeline, from model export to runtime serving, ensuring performance and reliability.
Our summary of the posting; the original is on the Hume AI careers page.
What the posting requires
- Required
- Linux
- Troubleshooting
- Rust
- Distributed systems
- Profiling
- Python
- AI coding tools
- Go
- Load balancing
- Optimization
- Preferred
- GPU inference
- Numerical correctness
- Client libraries
- Containers
- Open source contributions
- CUDA
These tags are our reading of the posting. They can miss something; the original posting is the reference.