Remote Senior Python AI Engineer: LLM Fine-Tuning & RLHF

Hired; Lucca; Remoto; EUR 70.000 - 110.000; Tempo pieno

Descrizione del lavoro

Hired is seeking a Senior Python Developer to join a client project aimed at advancing large language models. This fully remote role lets you contribute from anywhere while helping curate proprietary data for fine-tuning and benchmarking.

You will design efficient Python code for training and optimization, participate in supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF), and evaluate model responses to ensure quality.

Competenze

• Proficiency in Python and AI/ML frameworks.
• Experience with supervised fine-tuning (SFT) and RLHF.
• Strong evaluation and benchmarking methods for AI models.
• Able to design Python code for data generation and model optimization.
• Familiar with AI model response evaluation and ranking methodologies.

Mansioni

• Design, develop, and maintain Python code to train and optimize AI models.
• Conduct evaluations to benchmark model performance and improve results.
• Evaluate and rank AI model responses across domains.
• Lead supervised fine-tuning and create high-quality datasets.
• Collaborate with researchers and annotators on RLHF and reward models.

Conoscenze

Python

AI/ML frameworks

SFT

RLHF

Evaluation & benchmarking

Data generation

Model optimization

Ranking AI outputs

Descrizione del lavoro

Hired is seeking a Senior Python Developer to join a client project aimed at advancing large language models. This fully remote role lets you contribute from anywhere while helping curate proprietary data for fine-tuning and benchmarking.

You will design efficient Python code for training and optimization, participate in supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF), and evaluate model responses to ensure quality.