About the role
The Token Factory team develops a serverless service for operating and tailoring large language models. The Principal ML Solutions Architect serves as the top technical consultant for clients, creating and deploying efficient model processes. This position also guides technical strategy for major clients and shapes the service's future evolution.
Our summary of the posting; the original is on the Nebius careers page.
What the posting requires
- Required
- Inference optimization
- LLM
- Inference framework
- Python
- Quantization
- Fine-tuning
- Evaluation
- vLLM
- API
- Preferred
- OSS
- Research
- DevOps
- Mlops
- Kubernetes
- AWS
These tags are our reading of the posting. They can miss something; the original posting is the reference.