Looking for a job

Zara Shafiq

@zarashafiq

QA engineer testing AI systems. LLM evaluation, Playwright/TypeScript, API testing. Sole QA across three production AI products.

Pakistan

Message

What I'm looking for

QA and AI-evaluation roles where I own testing end to end. I'm most useful on products where output isn't deterministic and standard assertions don't work.

I'm the sole QA at an AI product company, with final release sign-off across three production AI products: an AI people-search platform, a meeting transcription tool, and a virtual-office collaboration app.

Most of my work is testing LLM features whose outputs change between runs. I built the evaluation practice there from nothing: golden datasets, repeat-run consistency measurement, and a scorer framework covering rule-based checks, semantic overlap and LLM-as-judge. I also wrote an adversarial red-team suite mapped to the OWASP LLM Top 10.

On the automation side I replaced over a day of manual regression per release with 130+ Playwright and TypeScript tests across 60+ specs running in CI. Last year I documented 80+ defects, including a P0 where the flagship search silently returned 0 results against 329 on an identical query.

Four years total, across AI, healthcare under HIPAA, and EdTech — all on US-headquartered distributed teams. I've published an npm package for Playwright flake triage and my evaluation framework is public on GitHub.

Open to worldwide remote and relocating.

Experience

Work history, roles, and key accomplishments

Current

Software Quality Assurance Engineer

Current

QLU.ai

Nov 2024 - Present (1 year 10 months)

Sole QA with release sign-off across three AI products. Built the LLM evaluation practice from scratch: golden datasets, repeat-run consistency checks, and rule-based, semantic and LLM-as-judge scorers. Own a 130+ test Playwright/TypeScript suite in CI that replaced a day of manual regression per release.

Postman Python Playwright TypeScript LLM Evaluation AI Testing API Testing CI CD Test Automation Framework

Software Quality Assurance Engineer

OneScreen

Sep 2023 - Oct 2024 (1 year 1 month)

Manual and automated QA across 6 EdTech products on web, Android and touchscreen hardware. Validated AI features including quiz generation and transcription accuracy. Caught a Stripe billing bug pre-release and validated the full subscription lifecycle. API testing in Postman, performance testing in JMeter.

Regression Testing Performance Testing JMeter Postman API Testing Mobile App Testing

Software Quality Assurance Engineer

CareCloud

Oct 2022 - Sep 2023 (11 months)

Tested EHR and medical billing software (TalkEHR, TherapyEHR) under HIPAA compliance, supporting 99% defect-free releases. Logged, tracked and verified 500+ defects across the product line. Automated ~80% of assigned regression cases in Cypress. Caught a payment calculation bug that would have caused incorrect billing for therapy sessions.

Cypress JavaScript Test Planning Regression Testing SQL HIPAA API Testing

Android Developer

Maven Logix

Mar 2021 - May 2021 (2 months)

Built and debugged Android features in Java on production app tasks, then applied the same work to my final year project. A developer background that informs how I approach white-box test design.

Android Debugging Java

Software Quality Assurance Intern

Fusion Logix Pvt. Ltd

Sep 2020 - Nov 2020 (2 months)

First QA role. Wrote and maintained bug reports, tracked defects through to resolution, and contributed to internal QA standards and process documentation.

Bug Reporting Defect Triage Documentation

Education

Degrees, certifications, and relevant coursework

National University of Sciences and Technology (NUST)

Master's degree, Computer Software Engineering

2021 - 2024

Grade: 3.8

Pursued advanced studies in Computer Software Engineering, focusing on complex software development and quality assurance. Gained expertise in designing and implementing robust software solutions.