QA Engineer — exploratory testing beyond automation

Remote · part-time · contract · overlapping with 09:00–15:00 Dubai time (UTC+4)

About the product

InterMIND is a communication space for teams that work across languages: meetings, chat, documents and recaps, each participant seeing and hearing everything in the language they think in. Web, iOS and Android, desktop; several participants with roles (host, member, guest); 17 interface languages; live voice translation, translated chat, document translation. Real-time media over WebRTC, a translation engine in the path, and every one of those things running on whatever device and network the participant happens to have.

What automation already covers — and what it cannot

We run unit, integration, end-to-end and multi-actor chaos suites on every push, and an AI reads production errors every morning. Simple, deterministic paths are covered; we do not need a person to click through them.

What no script covers, and what this role owns:

Many devices, real networks. Laptop plus two phones, Bluetooth headset switching mid-call, Wi-Fi → LTE hand-over, a captive portal, a corporate proxy, the app backgrounded during a call, a tab throttled by the OS.
Perceived quality. Is the translated voice intelligible, is its timing usable in a real conversation, does the meaning survive — names, numbers, negations, idioms, two people speaking at once? Is audio clean after a reconnect? Only a person can judge this, and it needs a rubric, not a feeling.
Exotic paths. Role changes mid-call, a guest and a member with the same name, screen share plus laser pointer plus chat translation at once, RTL and CJK interface languages, a calendar-created meeting joined from the wrong account, a recap read in a language nobody in the call spoke.
Reasoning about cause. Not "it broke" but "it broke on the second device only after the host muted — here is the replay, here is the console, here is what I think is happening".

What you will do

Explore the product from short charters we give you (an area, a hypothesis, a device set). You decide how to break it and where to look next.
Report what you find through the product's own Give Feedback — it captures the screen, the console, the browser and the session replay for you; you add the recording, what you did and what you saw. No forms, no spreadsheets.
Write short quality assessments where a bug report is the wrong shape: translation adequacy on real speech, audio after network events, the usability of the translated voice — scored against a rubric, with examples.
Re-check fixes when asked, and tell us when a fix changed something else.

Who fits

Technical. You read a console and a network tab, you know what ICE, codecs and packet loss are or can learn them in a day, you can drive a phone over adb, throttle a connection, switch audio devices and say precisely which build you were on.
Creative. You look for the paths nobody wrote down. Filling in the same checklist every day is not this job.
Experienced. Several years of testing real-time, media or multi-user products count for a lot here — you already know where such systems break. Experience matters as much as the trial itself.
Languages. English good enough for precise reports; at least one more language you speak natively or near-natively, because translation quality is judged by ear.
Reliable availability at agreed hours.

How we hire

A paid one-week trial — the task is public: three charters on exactly the hard areas above, reported through the product. Evaluated on how much of what you found we can confirm, and on the quality of your judgment where confirmation is not the point.
Contract if the trial goes well: hourly, remote, an agreed weekly schedule.

What you need

A laptop with a webcam and a headset, at least one smartphone (two — one Android, one iOS — is a plus), a Bluetooth headset, and a network you can deliberately make bad.

Apply

Send a short note about yourself, the real-time or media product you tested most recently, and one bug you found in it that a script could not have.