Reyan Tariq

Software Engineer (previously International Graduate, Technology)

• Digitised credit card and personal loan fulfilment operations (~500 applications/month) by migrating legacy processes onto a centralised platform.
• Automated regulatory reconciliation of 45,000+ monthly financial transactions for Pakistan's federal tax authority, cutting a 3-hour weekly manual process to minutes.
• Engineered a Python rule engine consolidating monthly datasets and validating withholding-tax applicability.
• Reduced a daily operations workflow from 60–90 minutes to seconds; extended the approach to IFRS 9 Islamic Banking validation and technology-obsolescence reporting.
• Delivered a self-service regulatory data portal that lets non-technical teams run compliance queries themselves, saving ~10 hours/week of manual data requests.

DevOps Trainee

• Deployed and maintained Java financial applications across SIT, UAT, Pre-Production and Production.
• Monitored system performance with Checkmk, Grafana and Prometheus to keep financial transactions uninterrupted.

Technology Intern

• Designed AI-driven transcription and a Linear SVC text classifier, improving call routing by 50% across 100K+ calls/month.
• Performed exploratory data analysis on incident reports with Pandas and Seaborn, reducing issue resolution time by 15%.
• Managed SIT/UAT environment provisioning for the Payment-to-Merchant QR rollout, improving testing throughput by ~40%.

Founder

• Generated PKR 0.24 million in sales revenue in Q2 2021, fulfilling 100+ orders of tech accessories.

Commerce for a mentoring practice: a shop for physical and digital products, courses, paid one-to-one consultations and Stripe checkout, running on a Medusa commerce backend.

Next.js · Medusa · PostgreSQL · Stripe

An events app that matches organisers with the right vendors. A Python recommendation engine does the matchmaking; vendors get a dashboard for bookings, revenue and ratings.

React Native (Expo) · Flask · Neon Postgres

Bridges the gap between students and employers: real work from real companies, rewarded through a token system students can show off.

React · .NET · Clerk OAuth · Neon Postgres

Sorts consumer financial complaints (CFPB data) into product categories: credit cards, mortgages, debt collection, student loans. Five models compared; a tuned SVM won.

Python · scikit-learn · TF-IDF

Fine-tuned German BERT on 2,429 parliamentary speeches to predict a speaker's political orientation. 89% accuracy overall.

PyTorch · Hugging Face · Gradio

PAK-AI: Cultural Heritage Visualization Platform

MERN-stack platform with AI image generation, enabling community sharing of cultural content.