Intern Researcher – Agentic AI

About the role

Research, design, and implement novel LLM-based agent architectures for planning, reasoning, and decision-making. Explore agent memory, reflection, self‑evaluation, and feedback loops to enable continual learning and self‑improvement. Survey recent developments in the field and communicate findings with team members. Perform experiments, evaluate results, analyze data, and derive insights.

Key responsibilities

• Research, design, and implement novel LLM‑based agent architectures for planning, reasoning, and decision‑making.
• Explore agent memory, reflection, self‑evaluation, and feedback loops to enable continual learning and self‑improvement.
• Survey recent developments in the field and communicate findings with team members.
• Perform experiments, evaluate results, analyze data, and derive actionable insights.

Required profile

• Currently a PhD or Master's student in computer science or related fields.
• Hands‑on project experience building agent systems for planning and reasoning.
• Familiar with reinforcement learning (RL), ReAct, and Chain‑of‑Thought (CoT) tool calling.
• Strong AI/ML coding skills in Python; experienced with PyTorch.
• Good communication skills, willingness to collaborate and self‑motivated.
• Excellent oral and written communication skills.

Required skills

• Python
• PyTorch
• Reinforcement Learning
• ReAct
• Chain‑of‑Thought