Research Engineer, Production Model Post Training

TL;DR

Research Engineer (AI/ML): Implementing, scaling, and improving post-training techniques for frontier models with an accent on Constitutional AI, RLHF, and other alignment methodologies. Focus on designing robust pipelines, debugging complex training issues, and translating research into production-ready implementations for production Claude models.

Location: Zürich, Switzerland (hybrid, 25% in office)

Company

hirify.global is a public benefit corporation building reliable, interpretable, and steerable AI systems with a mission to make AI safe and beneficial for society.

What you will do

• Implement and optimize post-training techniques at scale on frontier models.
• Conduct research to develop and optimize post-training recipes that directly improve production model quality.
• Design, build, and run robust, efficient pipelines for model fine-tuning and evaluation.
• Develop tools to measure and improve model performance across various dimensions.
• Collaborate with research teams to translate emerging techniques into production-ready implementations.
• Debug complex issues in training pipelines and model behavior.

Requirements

• Strong software engineering skills with experience building complex ML systems.
• Comfortable working with large-scale distributed systems and high-performance computing.
• Experience with training, fine-tuning, or evaluating large language models.
• Bachelor's degree in a related field or equivalent experience.
• Proficiency in Python, deep learning frameworks, and distributed computing.
• English: B2 required.

Nice to have

• Experience with LLMs.
• Keen interest in AI safety and responsible deployment.
• Preference for senior engineers with hands-on experience with frontier AI systems.

Culture & Benefits

• Competitive compensation and benefits.
• Optional equity donation matching.
• Generous vacation and parental leave.
• Flexible working hours.
• Collaborative group with frequent research discussions.
• Visa sponsorship available.

Hiring process

• All interviews are conducted in Python.