Location: Cairo, Egypt (remote / hybrid) · Reports to: Head of Operations - MENA
About Lua
Lua is the Agent OS. We build digital employees — agents that do a real job end to end: they read a company’s own systems, make the decision, take the action, and get a little better every time they run. Not chatbots that answer questions — digital workers that do the work, on the company’s own data and workflows, and everything they build stays owned by the business. Teams write their logic on Lua (agents, skills, tools, jobs, webhooks, guardrails) and we run the hard parts underneath: infrastructure, multi-provider model orchestration, data, channels (WhatsApp, Slack, Email, Instagram, Messenger, a voice-capable website widget, HTTP API) and monitoring.
Our customers are the companies that run their markets — the operator of one of the world’s most-visited heritage sites, a major travel-and-hospitality group, the largest supermarket chain in its country, a listed conglomerate spanning healthcare and consumer goods, large regional banks, social-commerce companies and a microinsurer covering over a million people — across Africa, the Middle East and South Asia. Together they employ 64,000+ people and turn over $5bn+ a year, and they all want the same thing: to be AI-native on the systems they already run, with nothing to rip out. Backed by Y Combinator, we’ve raised $5.8M — and this is a chance to build the playbook, not inherit one.
Responsibilities
We’re looking for a junior engineer to join the implementation team and help build and deploy AI agents for our mid-market customers. You’ll work alongside a senior implementation engineer, learning the Lua platform and contributing to live customer projects from your first week.
This is an apprentice-track role with a clear growth path. You’ll start with structured work — environment setup, testing, knowledge base configuration — and grow into owning full implementations within 6 months.
Build agent skills and tools in TypeScript using the Lua CLI — the functions that let agents take real actions like API calls, data lookups, and webhook triggers.
Set up and configure agent environments: sandbox for development, production for live deployments.
Configure and manage client knowledge bases — the information agents use to answer questions and follow business rules.
Run QA and testing cycles before deployment — test across channels (WhatsApp, web, Slack) and flag issues.
Support the senior engineer on active implementations across the full build lifecycle.
Write and maintain technical documentation for each implementation.
Requirements
1–2 years writing code — professional experience, bootcamp, side projects, or university projects. You need to be comfortable in TypeScript or JavaScript.
Familiarity with REST APIs, JSON, and basic web architecture. You know what an endpoint is and how to test with Postman or similar.
A fast learner who figures things out by doing, not by waiting for instructions. The platform, CLI, and agent architecture will all be new.
Strong written communication — you’ll be in Slack daily, writing updates, flagging blockers, and documenting your work.
Reliable. When you say something is done and tested, it needs to actually be done and tested.
Fluent in Arabic and English
Nice to Have
Experience with any chatbot or conversational AI platform.
Familiarity with WhatsApp Business API, Slack API, or similar messaging platforms.
Comfortable with Git, GitHub, and CLI tooling.
Previous remote work experience.
Growth Path
Months 1–3: Support builds, learn the platform, follow the runbook, handle structured work.
Months 3–6: Own specific integrations within an implementation. Run client test sessions.
Months 6–12: Own an implementation end-to-end. Client-facing. Responsible for time-to-value on your accounts.
What We Offer
Fully remote — work from anywhere. Team spans UK, Africa, MENA, and Asia.
Small team, massive ownership. No bureaucracy. Ship and iterate.
Direct access to the founding team. Your work is visible and impactful from day one.
A platform that’s actually in production with real customers — not a pre-product startup.
