Manual QC / QA
We are looking for a detail-oriented and technically curious Manual QC/QA specialist for two related AI products: OpenClaw and AI Factory. Both projects are platforms for creating and managing AI bots with a Telegram interface.
This is not a “button-clicking” role — it’s important to understand how systems work under the hood and to identify the root causes of issues, not just report that “something is broken.”
Project 1: OpenClaw (ZeroClaw)
What is it?
OpenClaw is an intelligent AI assistant for a CEO. It runs on a virtual server in Google Cloud and communicates with users via Telegram. The bot can:
Answer questions and assist with tasks
- Work with Gmail (read, send, and classify emails)
- Integrate with Google Calendar and Google Sheets
- Perform business tasks: information search, data analysis, planning
- Integrate with external services (ClickUp, Slack, WhatsApp)
In addition to the bot, there is an admin panel called SwarmClaw — a web interface for monitoring the state of all system components.
What needs to be tested
1. Telegram bot - Verify that the bot responds to commands (/help, /skills)
- Monitor response quality (no leakage of internal tags or raw technical data)
- Test integrations with Google services via the bot
Ensure proper formatting of outputs (lists, tables)
2. Email processing (CEO Mailbot)
- Urgent emails should be delivered to Telegram with quick reply options
- Regular emails should be accumulated and delivered as a morning digest
- Spam should be automatically archived without notifications
Action buttons (Send, Edit, Snooze, Archive) must work correctly
3. SwarmClaw admin panel
- Ensure all bot components are displayed as “alive”
- Test sending commands to bots via the web interface
Verify configuration and settings
4. Stability and availability
- The bot should be available in Telegram almost all the time
- It should recover quickly after server restarts
Logs should be readable and informative
Project 2: AI Factory
What is it?AI Factory is a Bot-as-a-Service platform. Through a user-friendly web interface, users can create their own Telegram bot, select plugins (e.g., AI chat, data analyst, recruiter), and the platform automatically deploys the bot in the cloud.
Essentially, it is a bot builder that requires no coding or server setup.
What needs to be tested
1. Bot creation process- The user enters a Telegram bot token — the bot is created and launched automatically
- The full process (from creation to launch) takes only a few minutes
Bot status is displayed in the interface (creating, starting, running, error)
2. Plugin marketplace
- Users can browse the plugin catalog
- Install plugins to their bot
- Remove plugins
After installation, the bot must start using the plugin’s functionality
3. Bot lifecycle
- Start and stop the bot
- Delete the bot (and its associated infrastructure)
Restart after configuration changes
4. Security and isolation
- Users can only see their own bots
- It must be impossible to access another user’s bot
Different roles (owner, admin, viewer) have different permissions
5. Web interface
- All pages must load correctly
- Support switching between light and dark themes
- States like “loading,” “empty,” and “error” should be displayed properly
Forms must not submit if required fields are missing
General Requirements for the Candidate
Professional skills
- At least 1 year of experience in web application testing
- Ability to write test cases and checklists
- Understanding of testing types: functional, regression, smoke testing
- Experience with bug trackers (Jira, YouTrack, or similar)
- Basic understanding of APIs (GET/POST requests)
Nice to have - Experience with cloud platforms (Google Cloud, AWS)
- Understanding of Docker containers
- Experience testing Telegram bots or messaging platforms
- Basic Linux skills (log reading, basic commands)
- Experience testing chat interfaces or AI systems
Personal qualities - Attention to detail — ability to spot minor bugs and UI inconsistencies
- Technical curiosity — желание понять, как система работает “под капотом” → desire to understand how systems work under the hood
- Independence — ability to разобраться using documentation
- Accuracy — ability to clearly describe bugs so developers can reproduce them
- Prioritization skills — understanding that critical bugs outweigh minor improvements
What we offer - Work on interesting AI products in a friendly team
- Opportunity to impact product quality and see the results of your work
- Flexible schedule (remote or hybrid)
- Career growth: from Manual QC to automation or quality analyst roles
Sample tasks for the first month - Perform regression testing of OpenClaw after updates
- Test new plugins for AI Factory before release
- Prepare a checklist for regular smoke testing.
- Identify and document bugs in current products
- Verify integration with new Google services
Required languages
| English | B2 - Upper Intermediate |
| Ukrainian | C2 - Proficient |