Computer Science major at UC, building intelligent systems at the intersection of production software engineering and computer vision research.
Working alongside a research team validating and expanding REBL, an end-to-end, LLM-powered framework that automatically reproduces Android crash and non-crash functional bugs using raw textual report descriptions.
- Active Focus: Testing bug reproduction robustness across varying physical device matrices, OS configurations, and edge environment constraints.
- Technical Footprint: Evaluating feedback-driven context prompts against UI Automator2 structures to optimize multi-action sequence executions and circumvent traditional token threshold limitations.
π€ Local RAG Enterprise Engine | UC-Intelligence-Hub
- Architected a fully localized Retrieval-Augmented Generation (RAG) platform using FastAPI, LangChain, and ChromaDB to parse and query university partnership records securely.
- Embedded an asynchronous SharePoint REST pipeline wrapped in Microsoft Entra ID authentication and coupled it with FlashRank document rerank algorithms to suppress LLM hallucination indexes.
π Biomechanical Kinematics & Signal Processing | GripForce-LoadForce | QTM-Realtime-Kinematics
- Data Transformation: Developed Python data transformation utilities to handle biomechanical signal data extraction, structuring time-series multi-sensor load distributions for force resistance analysis.
- Real-Time Streaming: Built real-time asynchronous streaming scripts using
qtm-rtto intercept live 3D marker coordinate trajectories directly from Qualisys Track Manager, mapping continuous hip and knee sagittal angles on the fly using vector dot-product geometry.
- Built and optimized deep 3D multi-class UNET segment models utilizing the MONAI framework to map structural heart features, achieving an average 0.88 Dice coefficient score and removing manual slicing latency bottlenecks.
- Configured pipeline preprocessing criteria and experimented with zero-shot segmentation leveraging Metaβs Segment Anything Model (SAM 2) to accelerate diagnostic testing loops.
π¬ Let's collaborate!
- πΌ LinkedIn: linkedin.com/in/abhishekchandra123
- π§ Academic Email: chandra6@mail.uc.edu

