AI Research Scientist, New Grad – Agents & Reinforcement Learning

Tech Stack

Responsibilities

• Design and develop agentic frameworks powered by recursive self-improvement loops
• Build and evaluate auto research agents capable of autonomously formulating hypotheses, executing experiments, and synthesizing findings
• Develop coding agents that understand, generate, and debug code across complex programming tasks
• Conduct research in reinforcement learning focusing on RLHF, DPO, and PPO
• Contribute to multi-agent systems where specialized agents collaborate to solve enterprise-scale problems

Culture

Requirements