I build multi-agent QA frameworks and LLM-evaluation pipelines for AI-driven distributed systems,
validating reasoning, not just outputs, with a human at every gate.
Most software teams treat quality as a testing phase. I've spent 8+ years proving it works better as a shared engineering discipline, embedded into requirements, system design, integrations, and user journeys before a single line of test code is written.
I partner with product, engineering, and design to ensure reliability is built in, not bolted on at the end.
My experience spans AI-powered workflow automation platforms, agentic orchestration frameworks, fintech and insurance products, event-driven architectures, and distributed backend systems across four industries.
Technical depth across AI validation, automation engineering, distributed systems, and product strategy.
8+ years across AI platforms, fintech, insurance, and digital evidence management.
Leading quality engineering for an AI-powered conversation intelligence platform built on distributed microservices and agentic orchestration workflows.
Owned quality strategy for a no-code AI workflow automation platform enabling businesses to build and deploy intelligent agents at scale.
Contributed to quality of commercial and industrial insurance platforms serving enterprise customers across European markets.
Worked on digital evidence and asset management platforms used in secure, high-compliance environments requiring strong data integrity standards.
Systems and frameworks I've designed and built end to end, from an agentic QA platform to cross-platform products and the backends behind them.
A 12-agent, human-gated framework that turns a scope link (an epic, story, or plain spec) into a merged, passing test suite (cases published, bugs raised with evidence, coverage recorded), with a human at five checkpoints, not an unattended robot.
@area and @type, making the suite pickable, so any subset runs on demand (--grep @area:checkout).Collections of the web that open the way you meant them to. A link points at a resource but cannot bound one, so anyone handing another person exactly one thing sends a link and hopes. Ferist adds the missing primitive at the moment a resource opens, on-device, over content it never touches: playback state may change; resource identity may never change. One shared, RN-free core drives iOS, Android, Web, and a browser extension on a Go backend.
@ferist/core) with types, viewer, sync engine, and platform ports, so one product contract drives four clients; platforms implement the ports, imports only flow downward.statement_timeout + backpressure/load-shedding, and instant revocation via a Redis suspension check.AppDelegate.swift, so offline capture and Keychain had never compiled while the build kept succeeding. Fixed and then verified by locating the RCTExternModule registration symbols per architecture in the built app — not by trusting a green build.flex: 1 centred column across all four auth screens; now centred in a growing scroll view, with the flow committed as a regression test.PrivacyInfo.xcprivacy manifest with NSPrivacyTracking false and no tracking domains.A full-stack petrol station finder with real-time pricing, crowd intelligence, and routing, built with Flutter and a Node.js microservices backend.
Promise.allSettled so crowd and pricing data enrich station results in parallel without blocking discovery on partial failures.
context.appColors.
A product concept for intentional, contextual device states: a phone that instantly becomes a “driving phone” or “exam phone,” exposing only the world the moment intends. Explored philosophy-first and validated with a clickable transformation prototype.
Actively exploring AI Quality Engineering leadership roles globally: senior IC, QA lead, or strategic quality roles at product companies building AI-powered systems.
Currently based in Karachi, Pakistan. Actively pursuing international opportunities, open to visa sponsorship and relocation.
I'll reply within 24 hours.