💼 About This Role

You'll build reinforcement learning environments and agents for real-world customer interaction workflows. You'll design reward models and enable learning from production data. This role offers direct exposure to 0→1 AI innovation in a fast-growing Series C company.

🎯 What You'll Do

• Design and build reinforcement learning environments for customer workflows.
• Define reward models using real-world signals and human feedback.
• Structure interaction traces into training-ready datasets.
• Experiment with multi-agent systems and simulation frameworks.

📋 Requirements

• Pursuing a degree in Computer Science, AI, or Machine Learning.
• Strong understanding of reinforcement learning fundamentals.
• Familiarity with RL environments and training libraries (e.g., Verl, Tinker).
• Strong foundation in probability, math, and optimization.

✨ Nice to Have

• Experience with RLHF or LLM/SLM fine-tuning.
• Exposure to agent-based systems or multi-agent RL.
• Prior research or publications in RL.

🎁 Benefits & Perks

• 🚀 Work on production-grade Agentic AI used by leading enterprises.
• 🧠 Build alongside experts from Amazon, Google, Meta.
• 💼 Series C fast-growing AI company with direct 0→1 innovation exposure.