LLM Fine-Tuning Engineer

About the role

Key Deliverables

List the expected deliverables for this project.

• Prepare and clean our domain-specific training dataset
• Set up and run fine-tuning experiments using LoRA/QLoRA
• Evaluate model outputs against baseline and set benchmarks
• Deploy the fine-tuned model for inference
• Document the training process and evaluation results

Requirements

Technical stack needed for this mission.

• Proven experience fine-tuning LLMs (LoRA, QLoRA, full fine-tuning)
• Strong Python and PyTorch
• Familiarity with Hugging Face Transformers and PEFT
• Able to set up training on cloud GPUs (AWS, GCP, or Lambda Labs)
• Experience evaluating fine-tuned model quality

Keep exploring related roles

Use these topic pages to discover more roles in the same hiring cluster.