Abdul Rafay@abdul-rafay19
2
Events attended
2
Submissions made
Pakistan
2+ years of experience
About me
I am a Software Engineering student and AI/ML enthusiast passionate about building intelligent, real-world AI systems. I work on LLM-based applications, RAG pipelines, and Agentic AI to develop chatbots, document-based QA systems, and automation-driven solutions. I have hands-on experience in Python, machine learning, and deep learning, along with projects in computer vision, NLP, and AI system development. My work includes building end-to-end ML pipelines, integrating AI models into scalable web applications, and applying techniques like prompt engineering, model optimization, and AI automation using tools such as n8n. I am particularly interested in creating impactful AI solutions that combine strong backend systems with practical, user-focused interfaces. I am always eager to learn, collaborate, and contribute to innovative projects in the field of artificial intelligence.
🤝 Top Collaborators
.png&w=640&q=75)
.png&w=640&q=75)
🤓 Latest Submissions
DRIFTZERO
DRIFTZERO is an autonomous code migration platform built to make SDK and API upgrades safer and more reliable. Developers provide a GitHub repository, source version, and target version. DRIFTZERO analyzes breaking changes and migration impact, creates a migration plan, applies code changes, generates or updates tests, validates the result, performs security and safety checks, and delivers the migration through an automated GitHub pull request when all verification gates pass. IBM Bob powers the reasoning layer of DRIFTZERO, including change analysis, impact analysis, migration planning, code migration, test generation, and recovery decisions. DRIFTZERO does not treat AI output as proof: generated changes are independently executed and validated through tests, builds, security checks, evidence collection, and deterministic safety gates. The end-to-end demonstration uses a real Express.js 4.22.3 → 5.x migration, while the architecture is designed for progressively verified migration families.
27 Sep 2026
BiasTrace
ML and data science students routinely train models on datasets with undocumented demographic imbalance, sampling bias, or geographic skew — and only discover it during peer review, a thesis defense, or after deployment, when it's too late to fix cheaply. BiasTrace catches this before training starts. Users paste a dataset's README, description text, or a Kaggle/HuggingFace URL. GPT-4o analyzes the methodology for known bias red flags — small or single-source samples, missing demographic documentation, no external validation set — and returns a 0-100 bias-risk score with severity-rated, evidence-backed flags. What makes BiasTrace different from a simple AI classifier: when a URL is provided, it uses Bright Data's live web integration to pull the dataset's actual public discussion or issues page and check whether bias has already been reported by other researchers. This grounds the analysis in real evidence instead of pure model judgment. Every audit closes with a concrete verification checklist and is saved to the user's private history for future reference. Built entirely in native.builder — the frontend, Supabase-backed auth and database, and Edge Functions were all generated and iterated on inside the platform, from PRD through deployment, with GPT-4o and Bright Data wired in as external integrations. Target users: ML/data science students, thesis writers, and early-career researchers who need a fast, evidence-based check before they train on or cite a dataset.
10 Aug 2026
