About

• Build Smarter LLM Agents: Design and develop next‑generation agents that go beyond simple task execution. You'll leverage memory, dynamic tool use, reinforcement learning, and multi‑agent collaboration to create robust, adaptive ecosystems that deliver real value in complex workflows. Drive Efficiency in LLM Applications: Pioneer innovations to make LLM applications faster, more scalable, and cost-effective. Your work will span context engineering, adaptive inference, and system level optimization across frameworks, reducing latency and resource usage without sacrificing quality. Participate in a 12-week internship program designed to provide hands-on experience and professional development. (Intern opportunities are available year-round, though they typically begin in the summer.) Collaborate with mentors, fellow interns, and researchers to conduct cutting-edge research and develop efficient AI algorithms and models. Engage in various research areas to broaden your expertise. Present your findings and actively contribute to the vibrant life of the research community. The ideal candidate has a strong foundation in machine learning and natural language processing, with experience in LLM applications or agent frameworks. You should bring curiosity, technical depth, and the ambition to apply research in practical settings, delivering innovations that move AI forward. Currently enrolled in a PhD program in Computer Science, Mathematics, or a related STEM field. Minimum 1 year of research experience, including peer reviewed publications and software development. Experience in building LLM agents and working with agentic frameworks, and/or in optimizing LLM-based applications for efficiency and scalability Strong research background with publications in top conferences/journals in one or more areas: natural language processing, machine learning, optimization, or statistics. Strong programming skills, preferable in Python. Excellent written and verbal communication skills.