AI Agent Engineer Intern

About the Role

Lexsi Labs is seeking AI Agent Interns to contribute to high-impact agentic AI projects across applied, research, and product domains. This internship involves working on real agentic systems, evaluation infrastructure, enterprise use cases, research prototypes, and product tooling.

Key Responsibilities

• Explore open-ended agentic AI problems and develop promising ideas into prototypes, experiments, research artifacts, or product capabilities.
• Build applied agents, design evaluations, create harnesses, experiment with planning and memory architectures, and analyze failures.
• Document findings and collaborate with research, engineering, and product teams.
• Potential outcomes include production-grade applied components, research contributions, papers, benchmarks, internal tools, or product prototypes.

Tracks

• Applied Agentic AI
• Build agents for enterprise use cases that reason over complex workflows, interact with tools and data systems, execute multi-step processes, and evaluate outcomes.
• Develop agents for enterprise workflows, structured or proprietary data, human-in-the-loop systems, and decision-support applications.
• Focus on building useful, reliable, and high-value agentic systems that solve real enterprise problems.
• Agent R&D and Evaluation
• Work on new ideas in agent architecture, harness design, evaluations, long-horizon reasoning, alignment, and interpretability.
• Build new agent harnesses, design evaluation frameworks, study agent failure modes, and benchmark tool use and planning.
• Contribute to research papers, technical reports, and reusable research infrastructure.
• Focus on producing research-quality insights, evaluation systems, benchmarks, or technical contributions.
• Product and Tooling Agents
• Build agents to enhance how researchers, engineers, and users interact with Lexsi systems.
• Develop tools like an AlignTune Agent for alignment workflows, AI Scientist-style agents for hypothesis generation, and tools for evaluating and debugging agents.
• Create product prototypes that transform research capabilities into usable workflows.
• Focus on building tools that increase the productivity of researchers, engineers, or enterprise users.

Requirements & Tech Stack

• Strong programming skills, preferably in Python.
• Hands-on experience with LLMs or AI systems.
• Strong interest in agents, evaluation, alignment, interpretability, or enterprise AI.
• Comfort working on ambiguous problems and building prototypes quickly.
• Ability to read papers or technical material and document findings clearly.
• Independently identify high-value directions.

Bonus Signals

• Experience with agent frameworks.
• Experience with long-horizon agents.
• Experience with evaluation pipelines.
• Experience with research projects.
• Experience with open-source tools.
• Experience with backend systems.
• Experience with enterprise data.
• Experience with AI safety and interpretability.