2025 Summer Intern, On-Device Information Retrieval Research Intern

Lab Summary:

Samsung Knox™ (https://www.samsungknox.com/) is Samsung’s guarantee of security, and a secure device gives you the freedom to work and play how, where, and when you want. Samsung Knox consists of a highly secure platform built into a variety of Samsung devices, including Samsung’s mobile phones and laptop computers.

Come join the Samsung KNOX team and help us define and develop the future core technologies for Samsung devices and services!

Position Summary:

Samsung Research America Advanced Knox R&D Team is looking for an intern to focus on retrieval-augmented generation (RAG) frameworks for enterprise productivity solutions. This role involves working on advanced information retrieval techniques, integrating knowledge graphs, vector search, and keyword-based hybrid search into AI-driven B2B applications. You will contribute to the next generation of retrieval systems that improve contextual understanding and relevance for on-device applications.

Position Responsibilities:

• Assist in building and optimizing retrieval-augmented generation (RAG) pipelines, integrating external data with LLMs for enhanced AI-driven solutions in the enterprise productivity space.
• Work on developing and deploying knowledge graphs, vector search, and keyword-based hybrid search to improve the performance of information retrieval systems.
• Collaborate with teams to fine-tune LLMs/ML Model and optimize them for use in retrieval systems, ensuring scalability and high performance.
• Develop proof-of-concept retrieval applications, evaluating their robustness and relevance in real-world enterprise scenarios.
• Implement efficient search frameworks and retrieval algorithms that leverage LLMs and other data sources on mobile.

Required Skills:

• Enrolled in a Ph.D. or Master's program in computer science, or related areas. Hands-on experience in information retrieval, knowledge graph construction, and vector search technologies.
• Strong knowledge of LLM architectures and their application in retrieval and hybrid search systems.
• Familiarity with RAG pipelines, NLP, and LLM fine-tuning, optimization techniques such as model pruning and model distillation.
• Proficiency in coding and prototyping using machine learning frameworks (e.g., PyTorch, TensorFlow).

Preferred Skills:

• Experience in deploying on-device LLM models.
• Experience with knowledge graph and vector search technologies.
• Passion for improving information retrieval systems in real-world enterprise productivity applications.