About the Role
We are seeking a highly motivated Parameter-Efficient Fine-Tuning (PEFT) Specialist to design, build, and support efficient model adaptation solutions using modern fine-tuning techniques such as LoRA, QLoRA, and related PEFT methods. The ideal candidate will work closely with business stakeholders, data scientists, and engineering teams to deliver secure, scalable, and measurable AI solutions.
Key Responsibilities
- Design and implement parameter-efficient fine-tuning solutions using LoRA, QLoRA, and PEFT frameworks.
- Fine-tune large language models while optimizing computational and memory efficiency.
- Develop and maintain training pipelines using PyTorch and related AI frameworks.
- Apply quantization techniques to improve model performance and reduce infrastructure costs.
- Conduct experiments, track model performance, and maintain reproducible workflows.
- Collaborate with data, engineering, and business teams to translate requirements into AI solutions.
- Evaluate model quality, accuracy, and efficiency metrics.
- Support deployment and optimization of fine-tuned models in production environments.
- Ensure security, scalability, and governance standards are followed throughout the AI lifecycle.
Required Skills
- Hands-on experience with PEFT, LoRA, and QLoRA
- Strong proficiency in PyTorch
- Knowledge of quantization techniques
- Experience with experiment tracking and model evaluation
- Understanding of large language models and fine-tuning workflows
- Familiarity with AI/ML development best practices
Experience Requirements
- Up to 5 years of overall experience
- Minimum 1–2 years of relevant hands-on experience in PEFT, model fine-tuning, or closely related AI/ML technologies
