AI Agent Engineer Intern

Role Overview

Lexsi Labs is a frontier AI lab focused on building aligned, interpretable, and safe AI systems for real-world deployment. We are looking for AI Agent Interns to work on high-impact agentic AI problems across applied, research, and product directions. You will work on real agentic systems, evaluation infrastructure, enterprise use cases, research prototypes, and product tooling.

Responsibilities

• Explore open-ended agentic AI problems and convert ideas into working prototypes, experiments, or research artifacts.
• Build applied agents for enterprise workflows and complex reasoning tasks.
• Design evaluation frameworks, agent harnesses, and benchmarking systems.
• Develop product tooling and agents to improve researcher and engineer productivity.
• Experiment with planning and memory architectures and analyze agent failure modes.

Requirements

• Strong programming skills, preferably in Python.
• Hands-on experience with LLMs or AI systems.
• Strong interest in agents, evaluation, alignment, interpretability, or enterprise AI.
• Ability to work on ambiguous problems and build prototypes quickly.
• Capability to read technical papers and document findings clearly.

Skills

• Python
• LLMs
• Agent Frameworks
• AI Evaluation
• Machine Learning