Fine-tune open-weight LLMs using SFT, LoRA/QLoRA and post-training methods such as DPO and GRPO. Diagnose model failures and turn them into experiments. Decide whether the answer is better data, post-training, prompting or classifiers.
- Apply on company site
- Benefits
- Equity
- Health insurance
- Paid time off
- Learning budget
- Wellness
Remote
AIChatgptClaude CodeConversational AIDevOpsEcommerceFine TuningGPU
View job