🛠 Tech Stack

💼 About This Role

You'll develop and implement novel techniques for training language models and agents with advanced reasoning capabilities, focusing on strategic decision-making in multi-agent environments. You'll create post-training and agentic methods to demonstrably improve AI behavior, working with a world-class research team. This fully remote role offers the chance to contribute to open-source AGI and collaborate with top researchers.

🎯 What You'll Do

• Develop novel fine-tuning and RL techniques using synthetic data from multi-turn interactions.
• Design agentic systems to improve reasoning on long-horizon strategic benchmarks.
• Create and maintain evaluation frameworks to measure reasoning skills.

📋 Requirements

• MS/PhD in Computer Science, ML, or related field (or equivalent experience).
• Strong programming skills in Python.
• Experience with ML model training and experimentation.
• Track record of implementing ML research.

✨ Nice to Have

• Experience with language model fine-tuning and post-training.
• Background in AI agents and/or reasoning research.
• Published work in AI.

🎁 Benefits & Perks

• 🏖️ Remote-first culture with flexible hours.
• 💰 Equity in a well-funded startup.
• 🧠 Collaboration with top AI researchers.
• 📚 Access to cutting-edge compute resources.
• 🌍 Global team with periodic in-person meetups.