I shipped a computer vision pipeline to production at EY, then audited a lending pipeline at AEREM.

The rest I build from scratch: an audit tool for LLM answer engines, a compiler, and a fleet dashboard for Claude Code agents. Computer science at NYU Tandon.

• beaconlive2026typescript→A local browser dashboard for every Claude Code session on a machine, with real control over agents it launches and a cross-project ticket board agents read and write over MCP.
• truviolive2026typescript, python→A three stage agent pipeline that measures how a brand surfaces across LLM answer engines, running three model APIs behind a single audit engine.
• vin pipelineshipped2026python→A computer vision pipeline that pulls vehicle identification numbers out of insurance claim video, shipped to production at EY.
• mapping berkeleyshipped2024python→A Google Maps style campus navigation system, with A* pathfinding and a feature that lets a user exclude zones from a route.
• brainlive2022rust→A compiler built from scratch for a custom language supporting arithmetic and variables: lexing, parsing, semantic analysis, and error reporting.

• AEREM Group, Net Zero Lendingjul 2026 to aug 2026Product management internAudited the solar EPC loan origination flow across its six stages, and flagged four drop-off and manual handoff points for remediation.
• EY, Forensic and Integrity Servicesmay 2026 to jul 2026AI and forensics internBuilt and deployed a computer vision pipeline that reads vehicle identification numbers out of insurance claim video, using YOLOv8 for detection and EasyOCR for the read, at 96 percent extraction accuracy for an Indonesian automotive client.
• Navi Mumbai Municipal Corporationaug 2023GIS and LiDAR internAnalyzed more than 500 properties against NMMC construction code using GIS records and LiDAR surveys, cutting verification time by more than 30 percent.

• New York University, Tandon School of Engineeringsept 2025 to may 2029B.S. Computer Science, minors in Data Science and MathematicsGPA 3.87. Tandon Dean's List, 2025 to 2026.

machine learning and vision

PyTorch, TensorFlow, NumPy, Pandas, Matplotlib, OpenCV, YOLOv8, EasyOCR, Qwen3-VL, LLM APIs: Claude, GPT, Gemini, Model Context Protocol

languages

Python, TypeScript, JavaScript, Java, C, C++, Rust, SQL

The rest of the stack, grouped by what I used it for, is on about.

• arnavdaultani@gmail.com
• ad7994@nyu.edu
• github
• linkedin