🛠 Tech Stack

💼 About This Role

You'll design and develop advanced reinforcement learning algorithms, build large-scale experiments, and integrate RL agents into production systems. Your work will directly shape next-generation AI capabilities in a remote-first environment with global collaboration. You'll tackle complex challenges like policy divergence and reward signal instability to push the boundaries of model performance.

🎯 What You'll Do

• Design and implement advanced reinforcement learning algorithms.
• Build and evaluate large-scale RL experiments with benchmarks.
• Develop high-quality simulation environments and training datasets.
• Optimize RL pipelines for exploration, stability, and efficiency.
• Integrate RL agents into production systems.

📋 Requirements

• Degree in Computer Science, AI, or related field; PhD preferred.
• Strong research background in reinforcement learning.
• Hands-on experience with large-scale RL experiments and online RL methods.
• Deep understanding of policy gradients, actor-critic, and policy optimization.
• Strong expertise in PyTorch and RL frameworks.

✨ Nice to Have

• Experience with multi-modal AI systems.
• Experience with resource-efficient model architectures.

🎁 Benefits & Perks

• 🏖️ Fully remote work environment with global collaboration.
• 🧠 Cutting-edge AI and RL technologies.
• 🌐 Exposure to multi-modal architectures and large-scale research.
• 📈 Career growth opportunities in a rapidly evolving tech environment.
• 🤝 Highly skilled international AI researchers and engineers.

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter screen· 30 min
2. 2Technical interview· 60 min
3. 3On-site/team interview· 45 min