AI Agent Intern (3-6 month)

Logitech is the Sweet Spot for people who want their actions to have a positive global impact while having the flexibility to do it in their own way.

The Role:

The intern will report to the IT Manager. This is a highly forward-looking and innovative role where you will step outside traditional development frameworks to participate in the architectural exploration and implementation of enterprise-level "Autonomous Agents." Your core mission is to assist the IT team in reshaping the human-machine collaboration model by introducing cutting-edge AI technologies to build intelligent assistants that can communicate, learn, and autonomously solve complex problems just like real teammates. You will have exciting career development opportunities, collaborating with a wide range of business departments to empower agile enterprise decision-making and drive comprehensive intelligence in daily operations.

Your Contribution:

• Incubate enterprise-level "Digital Employees": Assist in the deployment and secondary development of autonomous AI assistants, seamlessly integrating them into the team's daily work as true "digital employees."

• Design a self-evolving memory and skills system: Establish a growth mechanism for digital employee, much like training a new hire. By combining hybrid retrieval technologies (e.g., Hybrid Search using vectors and keywords) and dynamic context assembly, enable the digital employee to save and accumulate human corrections, nuances of business rules, and hidden logic through interactions, achieving a path of continuous self-learning from initial exploration to ongoing evolution.

• Build a multi-layer data Context Layer: Construct a rich business context layer for the data agent by integrating metadata, historical query logs, and domain expert descriptions, addressing the core pain point of AI lacking business background when querying complex enterprise data.

• Tool extension and integration: Enable digital employees to go beyond simple dialogue and autonomously invoke external tools (such as reading files, checking calendars, processing emails, or executing automation scripts) just like a real employee.

• System evaluation and safety guardrails: Establish a systematic evaluation mechanism to continuously monitor the accuracy of AI outputs; for high-privilege operations of the digital employee, assist in designing safety guardrails based on sandbox isolation or command approval flows (Allowlist) to intercept dangerous instructions and ensure enterprise data and environment security.

Your Qualifications and Skills:

• Currently pursuing a Bachelor's degree or above, majoring in Computer Science, Artificial Intelligence, Information Systems, or a related field.

• Solid Python programming skills and familiarity with API calls for Large Language Models (LLMs).

• Agent Architecture Awareness: Understand or have hands-on experience with open-source AI Agent frameworks or tools (such as Claude Code, LangChain, etc.), grasping the underlying logic of Tool Calling / ReAct (Reasoning and Acting) and autonomous agent loops.

• Memory and Context Engineering: Familiar with Retrieval-Augmented Generation (RAG) and the principles of vector databases, with a strong interest and practical experience in solving AI systems' "knowledge accumulation" and "long context management" challenges.

• Database and Analytical Skills: Proficient in SQL, capable of independently understanding and writing SQL scripts, and comprehending the underlying business logic and data flow behind the surface.

• Security and Engineering Awareness: Possess a foundational understanding of permission control, security isolation, and risk prevention awareness for AI systems.

• Communication and Collaboration: Excellent logical thinking, a strong spirit of exploration, and good oral and written communication skills in both Chinese and English. Able to patiently debug and train your "digital employee" like a "mentor."

• Actual development experience in complex Agent projects or contributions to open-source Agent projects on GitHub is highly preferred.

#LI-LZ1/51SZ/LP/INT

Across Logitech we empower collaboration and foster play. We help teams collaborate/learn from anywhere, without compromising on productivity or continuity so it should be no surprise that most of our jobs are open to work from home from most locations. Our hybrid work model allows some employees to work remotely while others work on-premises. Within this structure, you may have teams or departments split between working remotely and working in-house.

Logitech is an amazing place to work because it is full of authentic people who are inclusive by nature as well as by design. Being a global company, we value our diversity and celebrate all our differences. Don't meet every single requirement? Not a problem. If you feel you are the right candidate for the opportunity, we strongly recommend that you apply. We want to meet you!

We offer comprehensive and competitive benefits packages and working environments that are designed to be flexible and help you to care for yourself and your loved ones, now and in the future. We believe that good health means more than getting medical care when you need it. Logitech supports a culture that encourages individuals to achieve good physical, financial, emotional, intellectual and social wellbeing so we all can create, achieve and enjoy more and support our families. We can't wait to tell you more about them being that there are too many to list here and they vary based on location.

All qualified applicants will receive consideration for employment without regard to race, sex, age, color, religion, sexual orientation, gender identity, national origin, protected veteran status, or on the basis of disability.

If you require an accommodation to complete any part of the application process, are limited in the ability, are unable to access or use this online application process and need an alternative method for applying, you may contact us toll free at +1-510-713-4866 for assistance and we will get back to you as soon as possible.