AIML Intern
IIT Guwahati (Technology Innovation Hub) · Jul 2026 – Sep 2026
- Conducted research and evaluation of Vision-Language Models (VLMs) and Large Language Models (LLMs) for computer vision and multimodal AI applications, focusing on image, video, and object understanding.
- Contributed to a confidential railway computer-vision project (NFR), performing data annotation, segmentation, filtration, preprocessing, deduplication, and quality validation of image and video datasets; project details covered under NDA.
- Researched machine learning and speech-processing techniques, including STT and TTS and multilingual AI models, while supporting model evaluation, dataset analysis, and technical documentation.





