🛠 Tech Stack

💼 About This Role

You'll join a team building state-of-the-art LLMs, focusing on reinforcement learning methods for large-scale post-training. Your work directly improves models shipped to customers, pushing the boundaries of AI capabilities in Europe.

🎯 What You'll Do

• Conduct large-scale LLM training runs and analyze evaluation scores.
• Propose and implement hypotheses to maximize benchmark performance.
• Stay at the bleeding edge of RL research and iterate on novel approaches.
• Identify bottlenecks and optimize RL training loops for scale.

📋 Requirements

• Deep understanding of Reinforcement Learning theory.
• Experience with multi-node LLM training using RL.
• Familiarity with statistical methods for evaluation and experiment design.
• Strong Python skills and comfort with ML tooling (torch distributed).

✨ Nice to Have

• PhD in reinforcement learning or equivalent research experience.
• Contributions to top-tier venues (NeurIPS, ICML, ICLR) regarding RL.
• Experience evaluating LLM models and crafting environments for training.

🎁 Benefits & Perks

• 🏖️ 30 days paid vacation
• 🏋️ Wellhub fitness & wellness offerings
• 🧠 nilo.health mental health support
• 🏦 Subsidized company pension plan
• 🚆 Subsidized Germany-wide transportation ticket