Looking for a job

ALI UZAIR MEHDI

@aliuzairmehdi

Message

AI Quality Engineer at Astrello, improving healthcare LLM accuracy with evaluation suites and Playwright MCP agents.

Pakistan

Message

What I'm looking for

Remote AI Quality Engineer / Senior SDET role at a product company shipping AI. I want to build LLM eval pipelines (golden datasets, LLM-as-judge, hallucination checks) and own Playwright/TypeScript automation with CI/CD release gates. Based in Pakistan, full US EST overlap. Contract (Deel) or full-time. Available in 2 weeks; open to relocation with sponsorship.

At Astrello, I build and own automation, LLM evaluation, and agentic test workflows for a US value-based-care platform. My evaluation suites test an ACO-financials chatbot, an AI document reviewer, and other LLM features against golden datasets, with CI/CD release gates.

I also built a multi-agent test automation system on Playwright MCP and helped raise chatbot accuracy from ~78% to ~93% while reducing hallucinations from ~13% to ~3%. Previously, at Programmer's Force, I architected a Playwright/TypeScript framework supporting a 20,000+ scenario test ecosystem.

Experience

Work history, roles, and key accomplishments

Current

SDET (Contract)

Current

Astrello

Apr 2026 - Present (7 months)

Core quality engineer on a US value-based-care (ACO) platform, building and owning automation, LLM evaluation, and agentic test workflows across web, API, and AI features. Built evaluation suites for multiple LLM features, scoring accuracy, groundedness, and hallucination rate across 100+ golden test cases using LLM-as-judge, enforced as a CI/CD release gate.

Playwright Healthcare ACOs HIPAA LLM Evaluation Golden Datasets LLM As Judge Hallucination Detection Groundedness Testing Playwright MCP Multi Agent Testing SQL API Testing CI CD GitHub Actions

Senior SQA Automation Engineer

Programmer's Force

Feb 2025 - Apr 2026 (1 year 2 months)

Architected a Playwright/TypeScript framework supporting a 20,000+ scenario test ecosystem across 8+ verification modules and 10+ backend services. Automated 10,000+ scenarios, cut regression runtime by 40%, and led a team of 5 automation engineers.

Flakiness Reduction Playwright TypeScript Testing Automation Parallelization Test Architecture Team Leadership Mentorship Parallel Execution CI CD Jenkins Docker

Software Development Engineer in Test

Teamo

Jul 2023 - Feb 2025 (1 year 7 months)

Delivered QA for a US-based wellness e-commerce marketplace client, building UI automation with WebdriverIO, Selenium, and TypeScript covering 85-90% of critical user flows. Reduced regression time by ~75% and automated 12-15 backend services to ~70-75% API coverage.

WebdriverIO Selenium TypeScript API Testing BDD Test Planning Regression Testing CI CD Cucumber

Software QA Engineer

Emumba

Jul 2021 - Jul 2023 (2 years)

Validated an LLM-powered Interview Wizard, introducing prompt regression testing with golden datasets across 20-25 critical scenarios. Built Selenium/Postman/TypeScript frameworks, cutting manual regression time and improving early defect detection.