MSc Researcher · Ontario Tech University
AI engineer & graduate researcher working on trustworthy NLP for Requirements Engineering — LLM governance, knowledge discovery, and empirical software engineering.
MSc researcher working at the intersection of NLP and Requirements Engineering (RE). My thesis presents TRAC-RE — a Traceable, Reliable, Auditable, and Contextual framework for automated requirements engineering, structured as four interconnected phases that take raw stakeholder prose to structured, audit-grade knowledge artifacts: context-aware requirement identification, audit-grade keyword extraction, governed LLM parsing, and implicit keyword discovery. The framework is grounded in an industrial FinTech/SaaS corpus of 110 requirements and 1,997 High-Level JSON (HLJ) artifacts. Across three supporting papers (CASCON 2025 published, RE'26 Main under review, RE'26 RE@Next! in revision), I argue that governance and distributional alignment — not raw model scale — are the primary levers for trustworthy RE automation.
Current Focus
Thesis in progress
MSc, Software Engineering · Ontario Tech University
Supervisor: Prof. Sanaa Alwidian
TRAC-RE is a framework for automated requirements engineering (RE) built from four interconnected phases. Together they take raw stakeholder prose to implicit domain-knowledge discovery — spanning context-aware requirement identification, audit-grade keyword extraction, governed LLM parsing into structured JSON, and multi-signal implicit keyword discovery, all grounded in an industrial FinTech and SaaS corpus.
The four phases
Sentence-level classification with structured local-context features. F1 improved from 0.664 to 0.894 on 110 real-world FinTech and SaaS documents; 4K domain-aligned samples (F1=0.894) beat 15K mixed (F1=0.883) with 73% fewer samples.
Perfect-precision extraction that also surfaced a structural coverage ceiling of 1.5 canonical keywords per artifact, motivating the implicit-discovery phase.
Multi-model parsing into confidence-scored High-Level JSON with a versioned tag-governance stack. Tag precision improved from 0.657 to 0.897 (v2); +0.31 F1 over GPT-4.1.
A multi-signal engine — neighbor transfer, graph walks over an enriched 275,164-edge co-occurrence graph, and UMAP+HDBSCAN cluster-gap detection — grounded in a 13,725-entry domain dictionary, with full per-keyword provenance.
The throughline across all four phases: governance and distributional alignment, not raw model scale, are the primary levers for trustworthy RE automation. LLMs are powerful but don't belong in every role — in TRAC-RE they parse and they tiebreak, but they never generate ground-truth knowledge without a traceable, auditable trail.
The Research, Interactive
Most research lives in a PDF. Mine runs. Below is a short, guided walkthrough of the actual pipeline behind the three papers — in 2 steps. You'll see how the pieces connect, tune the knobs that drive the results, and watch the core finding play out on real requirement text. No prior context needed — each step explains itself.
Step 1 of 2 · What am I looking at?
A live map of how my work fits together — each circle is a paper, a research question, a dataset, or a finding, and the lines show how they connect. Click any node to read what it is. Drag to rearrange, scroll to zoom.
Step 2 of 2 · Now make it yours
These are the real knobs from my experiments — thresholds, models, training modes. Move a slider and the metrics (F1, precision, recall) update instantly from pre-computed results of actual runs. This is the ablation study, made playable.
Adjust parameters to explore pre-computed results
Results
F1
84.7%
Precision
94.9%
Recall
79.9%
Confusion Matrix
Want the full control room?
Everything above — the map, the knobs, the pipeline stages, and a simulated peer-reviewer that critiques the methodology — in one full-screen workspace. This is the closest thing to sitting next to me while I run experiments.
Selected Work
Dvip Patel, Sanaa Alwidian · CASCON 2025, 2025
A modular multi-model LLM pipeline that converts raw stakeholder requirements into High-Level JSON (HLJ) artifacts with confidence-scored fields, paired with a versioned tag-governance system that catches prompt-leak exploitation, hallucinated tags, and low-agreement outputs before they reach downstream stages.
Dvip Patel, Amarachi Nwosu, Sanaa Alwidian · RE'26, RE@Next!, 2026
Explicit keyword extraction — even at audit-grade precision — hits a structural ceiling of roughly 1.5 canonical keywords per HLJ artifact, with Jaccard agreement below 0.11 across KeyBERT, RAKE, and YAKE. This paper presents a 5-phase implicit keyword discovery engine combining a 13,725-entry domain dictionary, a 275,164-edge enriched co-occurrence graph, UMAP+HDBSCAN clustering, and a bounded LLM-as-judge that tiebreaks only the borderline scoring band. Every implicit keyword traces back to its discovery signal(s) with full per-signal evidence.
Dvip Patel, Sanaa Alwidian · RE'26, Main Track, 2026
An empirical study of sentence-level requirement classification on 110 real-world FinTech and SaaS documents (~5,700 candidate sentences, balanced to 15K mixed / 4K domain-only). We compare all-mpnet-base-v2 (110M) and DeBERTa-v3-base (184M) across frozen / LoRA / full fine-tuning and context window sizes k=0–3, and show that structured local-context features — not raw concatenation — are the critical signal.
Where I've worked
Oshawa, ON · Supervisor: Prof. Sanaa Alwidian
Remote · Part-time
Remote · Part-time
India
Built & Shipped
Gmail-native communication intelligence layer — one ingestion pipeline, six analysis modules.
Built at a 48-hour hackathon. Turns unstructured email into structured, actionable intelligence: a single ingestion + parsing core (Claude classifier, entity extractor, temporal indexer) feeds six independent modules — financial waste detection, relationship decay signals, contract/obligation tracking, follow-up commitments, a RAG-based institutional memory, and health-admin tracking. One parse, many consumers — no redundant API calls, and an entity graph that compounds over time. Currently being taken from hackathon build to a live product.
Autonomous 10-step AI migration agent for legacy Laravel codebases.
CLI-driven migration agent that ingests legacy Laravel code and runs analysis → planning → transformation → validation → self-healing loops. Processes ~10k LOC per run at under $80 cost, with 85–90% automated issue resolution.
A Traceable, Reliable, Auditable, and Contextual framework for automated Requirements Engineering — structured parsing, context-aware classification, and implicit keyword discovery.
The research framework behind my MSc thesis at Ontario Tech University. **TRAC-RE** — Traceable, Reliable, Auditable, and Contextual — converts raw stakeholder prose into audit-grade knowledge artifacts across four interconnected phases: 1. **Phase 1 — Context-aware requirement identification** — Sentence-level classification with structured local-context features. F1 improved 0.664 → 0.894 on 110 FinTech/SaaS documents; 4K domain-aligned samples (F1=0.894) beat 15K mixed (F1=0.883). Supporting paper under review at RE'26 Main. 2. **Phase 2 — Audit-grade keyword extraction** — Perfect-precision extraction that surfaced a structural coverage ceiling of 1.5 canonical keywords per artifact, motivating the implicit-discovery phase. Supporting paper in revision at RE'26 RE@Next!. 3. **Phase 3 — Governed LLM parsing (HLJ)** — Multi-model parsing (GPT-4.1, Claude Opus 4, Meta-70B) into confidence-scored High-Level JSON with versioned tag governance (v0 → v2); tag precision 0.657 → 0.897. Supporting paper published at CASCON 2025. 4. **Phase 4 — Implicit keyword discovery** — A 5-stage engine over a 275,164-edge enriched co-occurrence graph, with UMAP+HDBSCAN cluster-gap detection and a bounded LLM-as-judge tiebreaker. Supporting paper in revision at RE'26 RE@Next!. **Cross-cutting infrastructure** — 1,997 HLJ artifacts, a 13,725-entry domain dictionary, a FAISS index over 768-dim SBERT vectors, full per-decision audit logging, and drift monitoring across pipeline runs. The framework's central argument: governance and distributional alignment, not raw model scale, are the primary levers for trustworthy RE automation.
For the full engineering breakdown — story, stack, and impact — see the corporate view →
The Toolkit
Technical competencies
Requirements Engineering, NLP for Software Engineering, LLM Governance, Knowledge Discovery, Empirical SE
Python, TypeScript / JavaScript, PHP (Laravel), SQL, Bash
PyTorch, HuggingFace Transformers, sentence-transformers, SBERT / MPNet, MiniLM, DeBERTa-v3, KeyBERT, RAKE, FAISS, UMAP + HDBSCAN, LoRA Fine-tuning, RAG Pipelines, Anthropic / Claude API, MCP, Aider
React, Next.js, Tailwind CSS, Zustand
Laravel, Flask, REST APIs, Microservices, RBAC, Docker, AWS, CI/CD, GitHub Actions
Vitest, fast-check (property-based), Testing Library
Education
Thesis: “Toward Automated Requirements Engineering: Empirical and Architectural Foundations for Structured Parsing and Knowledge Discovery”
Certifications
Teaching & Authored
Let's talk
I'm open to research collaboration, AI engineering work, and good conversations about NLP for software engineering. The fastest way to reach me is email.