AI Engineer — NLP & Intelligent Systems. I ship end-to-end intelligent systems — from LLM pipelines and retrieval stacks to production Laravel migrations — with a bias toward trustworthy, auditable design.
Infrastructure
A live benchmark: four AWS deployment strategies run the exact same workload head-to-head and stream their real millisecond timings back as they finish. Hit start and watch actual infrastructure race — no mocks.
AWS Lambda with forced cold start — no warm container reuse
AWS Lambda kept warm via EventBridge ping every 5 minutes
Fastify on bare EC2 (t3.micro) behind Nginx — port 3001
Containerized Fastify via docker-compose on EC2 — port 3002
Races all 4 strategies simultaneously — typically 1–3 seconds
AI Demo
A real AI agent you can run. Pick a task, give it an input, and watch it reason, choose tools, call real APIs, and write a structured report — every step streamed live as it happens.
Select a task type, provide input, and watch the agent reason in real time.
Experience
Ontario Tech University · Oshawa, ON
Palomino Systems · Remote
Mediabridge · Remote
Finserve Infotech · India
Research
TRAC-RE: Traceable, Reliable, Auditable, and Contextual
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.
Supervisor: Prof. Sanaa Alwidian
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.
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.
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.
Want the full research write-up? Switch to the academic view →
Capabilities
Featured work
Two systems tell the story best: a production migration platform that pays for itself, and the research pipeline behind my thesis. Here's what each one does and what it's made of.
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.
What it's built with
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.
What it's built with
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.
What it's built with
Also on this page — live & playable
Four AWS deployment strategies benchmarked head-to-head with live millisecond timings.
A real tool-using AI agent that reasons, calls live APIs, and streams a structured report.
Open source
Contact
Happy to chat about NLP pipelines, LLM governance, autonomous migration systems, or graduate research collaboration. Email is the fastest way through.