Beschreibung
For our customer we are searching for a Language Model Fine- Tuning Specialist (f/m/d).
HintergrundActive fine-tuning of a large-scale language model on in-house data is underway, with the objective being the translation of natural language inputs into machine-readable JSON configurations.
The development of a promising end-to-end prototype has already been accomplished, which includes a custom data loader, a fine-tuned LLM, and model serving.
The next step involves the further enhancement of the model’s performance and the generalization of the approach to other data sources.
- Adapt our custom ETL pipeline to an updated training data scheme
- Craft a series of LLM prompts to generate broader training data
- Develop custom metrics to track the domain specific performance of the model on a custom test dataset
- Experiment and improve the model performance by fine-tuning larger multi-gpu models, with state-of-the-art tools like DeepSpeed, LoRa-Peft, GaLore optimizers and grammar based generation
- Serve the model via Databricks model serving API
- Deep understanding of NLP, complemented by hands-on experience in machine learning frameworks such as PyTorch, and a familiarity with NLP libraries like Hugging Face Transformers
- Experience in fine-tuning large language models like Flan-T5, and the knowledge of state-of-the-art optimization techniques and tools, including DeepSpeed, LoRA-peft, and GaLore optimizers
- Expertise in utilizing multi-GPU environments for distributed training, and a familiarity with tools and methods for optimizing machine learning models for high performance and efficiency
- Knowledge of Databricks, including API model serving, and the experience of deploying models in production environments at scale
- Strong programming skills in Python, and the ability to write code that is maintainable, efficient and reliable code
https://www.etengo.de/it-projektsuche/93541/