Multimodal AI (Vision) MSc/PhD Student

**Introduction** At IBM Research, we are the innovation engine of IBM. Exploring what’s next in computing and shaping the technologies the world will rely on tomorrow. From advancing AI and hybrid cloud to pioneering practical quantum computing, we anticipate challenges and unlock new opportunities for clients, partners, and society. Working in Research means joining a team that accelerates discovery at the intersection of high-performance computing, AI, quantum, and cloud. You’ll collaborate with leading scientists, engineers, and visionaries to push boundaries and turn ideas into reality. With a culture built on curiosity, creativity, and collaboration, IBM Research offers the opportunity to grow your career while contributing to breakthroughs that transform industries and change the world. **Your role and responsibilities** If you're a graduate student excited about the intersection of vision and large language models — and want to contribute to research with both academic and industrial impact — this position is for you. Our team at IBM Research develops models, algorithms, and technologies that drive IBM products and advance the broader open-source AI community. We publish at top-tier conferences (CVPR, ACL, and more) and release widely-used open-source models (>0.5M monthly downloads). As a student, you'll tackle real-world problems with cutting-edge methods to push the state of the art in vision-language models. You'll collaborate closely with researchers from both IBM Research and academia, and leverage large-scale GPU compute. This is a full-year part-time position at our Haifa or Tel Aviv research sites (flexible). Sample of the group's publications from the past year: * [1] CARES: Context-Aware Resolution Selector for VLMs, ACL 2026 (oral) * [2] ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding, CVPR 2026 * [3] CLIMP: Contrastive Language-Image Mamba Pretraining, ECCV 2026 * [4] Balanced Thinking: Improving Chain of Thought Training in Vision Language Models, CVPRW 2026 * [5] DocReRank: Single-Page Hard Negative Query Generation for Training Multi-Modal RAG Rerankers, EMNLP 2025 * [6] REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark, ACL 2025 * [7] Teaching VLMs to Localize Specific Objects from In-context Examples, CVPR 2025 * [8] LiveXiv — A Multi-Modal Live Benchmark Based on Arxiv Papers Content, ICLR 2025 References Visible links 1. https://arxiv.org/abs/2510.19496 2. https://arxiv.org/abs/2603.27064 3. https://arxiv.org/abs/2601.06891 4. https://arxiv.org/abs/2603.18656 5. https://arxiv.org/abs/2505.22584 6. https://arxiv.org/abs/2502.12342 7. https://arxiv.org/abs/2411.13317 8. https://arxiv.org/abs/2410.10783 **Required technical and professional expertise** * M.Sc. or Ph.D. student with a solid foundation in Machine Learning and Multimodal Large Language Models. * Strong command of modern methods and familiarity with recent literature; prior CV/ML/DL/LLM publications are a strong advantage. * Strong Python coding skills, including effective use of AI coding agents. Experience with Transformers and LLMs is an advantage. * A team player with strong communication skills and a genuine willingness to collaborate. IBM is committed to creating a diverse environment and is proud to be an equal-opportunity employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, gender, gender identity or expression, sexual orientation, national origin, caste, genetics, pregnancy, disability, neurodivergence, age, veteran status, or other characteristics. IBM is also committed to compliance with all fair employment practices regarding citizenship and immigration status.