Build a model customization and deployment lifecycle platform, including fine-tuning pipelines and evaluation harnesses. Develop platform APIs and observability layers to ensure auditable compliance for ISVs and CSPs.
Requirements:
Requires a Bachelor's degree in Computer Science or Engineering and over 7 years of experience with LLM serving infrastructure. Must have deep expertise in model quantization, fine-tuning workflows (LoRA, SFT), and robust API development.
Key Skills:
- LoRA
- QLoRA
- Supervised Fine-Tuning
- Reinforcement Learning
- Preference Optimization
- Retrieval-Augmented Generation
- vLLM
- TRT-LLM
- Model Quantization
- Platform API Development
- LLM Serving Infrastructure
- Model Evaluation
- Observability
- Compliance Auditing
- Cross-functional Collaboration
Benefits:
- Equity
- Generous benefits package
Senior Software Engineer, NIM Model Customization in santa clara at Unknown Company
This position is listed as full time and onsite.