AI Research Engineer - Custom Models & RL

Reply; Torino; Hybride; EUR 55 000 - 85 000; Plein temps

Avantages offerts par ce poste

Competitive salary

Structured career path

Continuous learning

Replyer benefits

Résumé du poste

Reply is a network of specialized companies seeking an AI Research Engineer expert in training custom AI. You will design synthetic dataset generation pipelines from task descriptions, teacher-student distillation, and post-training RL workflows on custom environments.

You will manage distributed clusters across local and cloud compute, optimize serving configurations, and share insights via blogs and open-source repositories.

Qualifications

• Degree in a quantitative field with strong programming foundations.
• 3–8 years of experience and 2+ years in training LLMs.
• Experience with dataset crafting and ablations is preferred.

Responsabilités

• Design synthetic dataset generation pipelines from descriptions.
• Train LLMs with mid/post-training approaches and RL focus.
• Run training on distributed clusters and optimize serving configs.

Connaissances

Curious

Proactive

Teamwork

English comms

Formation

Bachelor's degree in Computer Engineering / AI / Math / Software Engineering

Outils

Python

Triton

Rust

Description du poste

Reply is a network of specialized companies seeking an AI Research Engineer expert in training custom AI. You will design synthetic dataset generation pipelines from task descriptions, teacher-student distillation, and post-training RL workflows on custom environments.

You will manage distributed clusters across local and cloud compute, optimize serving configurations, and share insights via blogs and open-source repositories.