What the posting requires
- Required
- US citizenship
- Serving frameworks
- vLLM
- Sandboxed execution
- GPU memory hierarchies
- Model parallelism
- Kubernetes
- Benchmark
- Batching strategies
- Preferred
- Cost-per-token
- Inference fleet optimization
- GPU capacity
- Economics
- Commercial tradeoffs
- Computer Science
These tags are our reading of the posting. They can miss something; the original posting is the reference.