LLM Fine-Tuning Expert Required

Job Description: LLM Fine-Tuning Expert Needed We are looking for an experienced machine learning engineer to fine-tune Llama 3.1 or 3.2 models using small custom datasets.
Requirements

Proven experience fine-tuning LLMs, especially Llama models, with small datasets
Hands-on expertise with LoRA adapters (unsloth library)
Demonstrated ability to tackle overfitting challenges
Proficiency in optimizing hyperparameters and regularization techniques

Responsibilities

Fine-tune the Llama model using our custom dataset
Implement strategies to prevent overfitting
Document the fine-tuning process and results

Qualifications

Strong background in machine learning and NLP
Experience with PyTorch and Hugging Face Transformers
Familiarity with parameter-efficient fine-tuning techniques

Note: Only candidates with practical experience in fine-tuning LLMs on small custom datasets should apply. Please provide examples of relevant projects, focusing on challenges faced and solutions implemented.

Candidates who have only worked with pre-cleaned, publicly available datasets or are in the experimentation phase should NOT apply.