🛠 Tech Stack

💼 About This Role

You'll develop systematic approaches to RL environment design and analyze agent failure modes to create high-quality training benchmarks. You'll study how LLMs fail across task types and turn those insights into repeatable processes and benchmark suites. This role combines research intuition with practical execution at an applied AI research lab.

🎯 What You'll Do

• Develop recipes for creating RL environments that train and evaluate agents.
• Study how LLMs fail across task types to inform better environment design.
• Create benchmark environments for external release on the evaluation platform.
• Verify environment quality through hands-on agent testing and analysis.

📋 Requirements

• Strong foundation in ML through a PhD/MS in ML, CS, or equivalent industry experience.
• Proficiency in Python and ML frameworks like PyTorch or JAX.
• Experience with RL concepts and agent training.
• Comfortable working with cloud platforms (GCP, AWS) for experiments.

✨ Nice to Have

• Hands-on experience with reinforcement learning or agent training systems.
• Background in data curation, dataset creation, or evaluation benchmark design.
• Experience with AI safety, robustness testing, or adversarial evaluation.

🎁 Benefits & Perks

• 🏖️ Health coverage
• 🏖️ Flexible work arrangements
• 🏖️ Competitive salary and equity