(#8464682002) 2026 Intern, Agentic AI Solutions (Summer/Fall)
Lab Summary:
Advanced Intelligence Lab at Samsung Research America is working towards a vision of a world-class voice assistant that provides a unified AI experience across multiple devices (Galaxy Smartphones, Galaxy Watch & Smart home appliances like TVs, Family Hub, IoT devices etc.) with deep integration and building Agentic AI assisted solutions.
We work on applied research, innovative products, services, and experiences to delight our users by promoting advanced artificial intelligence technology to make best user experience with Bixby AI assistant to be intuitive, faster, seamless, more powerful, and multi-dimensional across different product domains/categories. Our goal is to improve user’s lifestyles through AI and related advanced technologies
Position Summary:
Bixby is an intelligent personal assistant which is only available as a built-in application on Samsung flagship devices and wearables. This is an advance intelligent system backed by an Agentic AI framework. This application uses Natural Language Understand users’ intentions and provide smart assistance by answering the questions and performing actions for users. Based on users intent Bixby can perform perform tasks on these devices, including but not limited to making phone calls, sending text messages, setting up meetings, opening apps, setting alarms and timers, getting directions, answering general questions, providing information about restaurants and other businesses, etc.
Samsung Bixby team is seeking talented and self-driven software engineering interns to join our applied research on Agentic AI on-device solutions. As an intern you will work closely with our team of engineers to develop and maintain software products, learn about the latest technologies and industry trends, and gain valuable experience in a fast-paced and dynamic work environment and build next generation Agentic AI services that influence the evolution of smart assistant solutions across our flagship devices.
Position Responsibilities:
- Deeply involve in devolving agents and tools used by Bixby agentic framework
- Develop Intelligent systems that use the LLM backed agentic framework to address expectation of Bixby as a next generation smart assistant.
- Design and implement algorithms to develop hybrid reasoning models that integrate multiple approaches and derive actionable insights
- Develop and fine-tune hybrid models with novel algorithms for on-device compilations and edge computations
- Set up processes to monitor and continually improve efficiency and performance of models by different methods of tuning
- Write high-quality production code as you build and maintain robust, scalable machine learning systems.
- Program primarily in Python and / or Java using efficient algorithms and software design patterns
- Participate in new product concepts and create proof-of-concept prototypes
- Function as an integral part of a larger team and collaborate and communicate effectively
Required Skills:
- Currently pursuing a MS or PhD Computer Science or equivalent field with knowledge around NLP, ML, AI, Agentic framework will be a plus
- Experience and proficiency in software development in any language
- Experience with deep learning architectures such as LSTMs, Transformers, Tree-LSTMs, Graph Neural Networks, etc.
- Knowledge of advanced ML techniques for improving recommendation accuracy and scalability based on content-based filtering methodologies
- Experience with deep learning frameworks like TensorFlow, PyTorch, JAX and libraries like Hugging Face transformers, Deep Graph Library, DGL-KE, etc. with specific requirements for Android devices
- Hands on experience with Web applications/services development in a professional environment
- Strong knowledge of design patterns and scalable architecture
- Strong understanding of computer science fundamentals such as algorithms, data structures and run-time analysis
- Ability to create self-contained, reusable, and testable modules and components
- Experience working in a complex large codebase and or in an open-source project is a strong plus
- Extensive experience with software prototyping or designing experimental software
- Analytical and problem-solving skills for design, creation, and testing of custom software