Senior Python AI Engineer — LLM Training & Benchmarking

Hired; Crémenes; Híbrido; EUR 60.000 - 90.000; Jornada completa

Descripción de la vacante

Hired, in collaboration with a leading AI company, seeks a Senior Python Developer to advance large language models by producing high-quality data for fine-tuning and benchmarking. You will design Python code for model training, evaluate performance, and rank responses across domains.

Responsibilities include leading supervised fine-tuning, collaborating with researchers and annotators on RLHF, and refining reward models to drive continual improvements.

Formación

• Proficiency in Python and related frameworks/libraries for AI/ML tasks.
• Experience with supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF).
• Strong understanding of evaluation strategies and benchmarking processes for AI models.
• Ability to design and implement Python code for data generation and model optimization.
• Familiarity with AI model response evaluation and ranking methodologies.

Responsabilidades

• Design, develop, and maintain efficient, high-quality Python code to train and optimize AI models.
• Conduct evaluations to benchmark model performance and analyze results for continuous improvement.
• Evaluate and rank AI model responses to user queries across diverse domains, ensuring alignment with predefined criteria.
• Lead efforts in supervised fine-tuning, including creating and maintaining high-quality, task-specific datasets.
• Collaborate with researchers and annotators to execute reinforcement learning with human feedback and refine reward models.

Conocimientos

Python

AI/ML frameworks

SFT

RLHF

Evaluation & benchmarking

Descripción del empleo

Hired, in collaboration with a leading AI company, seeks a Senior Python Developer to advance large language models by producing high-quality data for fine-tuning and benchmarking. You will design Python code for model training, evaluate performance, and rank responses across domains.

Responsibilities include leading supervised fine-tuning, collaborating with researchers and annotators on RLHF, and refining reward models to drive continual improvements.