---

I build ML systems that are meant to last. From LoRA fine-tuning experiments and agentic pipelines to deployed production automation. Engineering Graduate in AIML. I am 22.

My work spans LLM evaluation, self-supervised learning, representation learning, and practical MLOps. I care about reproducibility, clean architecture, and getting the metrics right before claiming anything.

---

Work

tldrun   Upload an ML paper PDF, get a runnable scaffold with training script, Docker, configs, and a reproducible ZIP — with anti-hype implementation notes surfaced automatically. TypeScript   React   Express   Vite	ftuneprompt 50+ LoRA experiments across 3 tasks and model families to answer: fine-tune or prompt? Ships a CLI tool that gives a concrete recommendation based on your task, data size, latency, and cost. Python   LoRA   QLoRA   Empirical ML
model-arena Terminal-native multi-agent reasoning arena where specialized agents (strategist, reasoner, critic, judge) debate in structured rounds and produce a scored verdict with tradeoffs. Python   OpenRouter   Rich   Multi-agent	recursive-knowledge-engine Full-stack RAG system built around a recursive self-refinement loop — retrieve, answer, critique, refine query, repeat — with ablation mode, calibration tracking, and failure logging. Python   FastAPI   FAISS   React
cycleflow Research prototype for flow-guided video inpainting. Uses RAFT optical flow and cycle-consistent temporal optimization to remove or replace objects without the usual flickering artifacts. Python   Stable Diffusion   RAFT   Computer Vision	lack-of-invariance Empirical study measuring how LLM answers shift under semantic paraphrasing. Introduces the Answer Invariance Score; mean score of 0.6968 across Mistral-7B on SQuAD reveals high phrasing sensitivity. Python   Mistral-7B   LLM Evaluation

Stack