Intern, Software Engineer AI Agents

About the Role

• Seeking a highly motivated Software Engineer Intern to join our AI Agents team.
• This team explores, prototypes, and productionizes cutting-edge AI agent technologies to accelerate productivity, automate workflows, and enhance knowledge sharing.
• Work on building and improving AI-powered agents that support software development, fleet operations, and business processes.
• Opportunity to experiment with the latest advancements in large language models (LLMs), agent frameworks, and autonomous workflows.

Key Responsibilities

• Design, build, and iterate on AI agents that automate engineering, operational, and business workflows.
• Develop integrations between LLMs and internal systems, tools, and data sources.
• Implement agent workflows involving planning, tool usage, memory, and multi-step reasoning.
• Experiment with prompt engineering, evaluation techniques, and model optimization strategies.
• Build backend services and APIs to support scalable deployment of AI agents.
• Collaborate with engineers and cross-functional teams to identify high-impact automation opportunities.
• Evaluate and benchmark emerging AI agent frameworks, models, and tools.
• Contribute to internal platforms that enable rapid development and deployment of AI-powered solutions.

Qualifications

• Currently pursuing a Bachelor’s or Master’s degree in Computer Science, Engineering, or a related technical field.
• Strong programming skills in Python (preferred) or other languages such as Go, Java, or JavaScript/TypeScript.
• Solid understanding of data structures, algorithms, and software engineering fundamentals.
• Familiarity with machine learning or large language models (through coursework, projects, or internships).
• Strong curiosity about AI systems and eagerness to explore new technologies.

Preferred Qualifications

• Hands-on experience with LLM APIs (e.g., OpenAI, open-source models) or agent frameworks (LangChain, AutoGen, etc.).
• Experience building backend systems, APIs, or distributed systems.
• Familiarity with prompt engineering, RAG (retrieval-augmented generation), or vector databases.
• Exposure to evaluation methods for AI systems (benchmarks, metrics, human-in-the-loop feedback).
• Experience with cloud platforms (AWS, GCP, Azure) or containerization (Docker, Kubernetes).
• Interest in applying AI to real-world problems such as automation, productivity, and decision-making.