Senior AI Researcher- Pre-training (f/m/d)

Highlights

• Build European foundation models for high-stakes finance and public use.
• Own architecture and training recipes from proxy tests to massive runs.
• Partner across data, eval and post-training to ship efficient models.

What they offer

• 30 days of paid vacation
• Access to fitness & wellness offerings via Wellhub
• Mental health support through nilo.health
• Substantially subsidized company pension plan
• Subsidized Germany-wide transportation ticket
• Budget for additional technical equipment
• Flexible working hours and hybrid working model
• JobRad Bike Lease

Ideal candidate

Rigorous researcher-engineer fascinated by training dynamics and scaling, who thrives on ownership, close collaboration, and turning careful experiments into reliable, efficient foundation models.

Requirements

• Proficiency in Python and PyTorch-based training workflows
• Strong track record in ML research and software engineering via shipped models, open-source or publications
• Strong mathematical foundation in optimisation, scaling behaviour and training dynamics
• Deep understanding of transformer training dynamics and large distributed training jobs
• Ability to design rigorous experiments and translate results into robust training decisions
• Hands-on experience pre-training large models (e.g. 7B+ parameters) on 100+ GPU clusters
• Strong software engineering practices including maintainable, well-tested, reproducible code
• Ability to implement complex architectures and debug across model, dynamics and distributed systems
• Effective collaboration and clear communication across research and engineering teams
• Ability to work in Germany and collaborate regularly on site in Heidelberg