AI Automation & Full-Stack Product Engineer

CerealBox; Pakistan; On-site; PKR 22,206,000 - 37,010,000; Full time

Benefits offered by this job

21 days leave

Leadership access

AI experimentation

Job summary

CerealBox Limited. is a UK-based creative and fundraising agency working with charities. We are seeking our first in-house AI Automation & Full-Stack Product Engineer to own True ROAS and build production tools that make the team smarter, faster and more effective.

You will identify automation opportunities, prototype solutions, and decide whether to build, integrate or buy. The role spans frontend, backend, data and AI, with a strong focus on delivering real business impact for charity

Qualifications

• '4+ years experience' in software engineering.
• Strong full-stack experience with React and TypeScript.
• Experience owning production systems.
• Experience integrating third-party APIs.
• Strong product thinking, not just coding from specs.
• Ability to design clean interfaces without waiting for perfect Figma files.
• Curiosity around AI, automation, agents and LLM APIs.

Responsibilities

• Own True ROAS production platform, used by media buyers, creatives and leadership.
• Identify repetitive work that can be automated.
• Prototype AI/automation solutions quickly.
• Decide build, integrate or buy for solutions.
• Turn experiments into reliable production tools.
• Keep AI systems current as models evolve.
• Build and maintain modern React and TypeScript applications.
• Own backend architecture, APIs and database logic.
• Work with PostgreSQL and Supabase.
• Maintain scheduled jobs and data pipelines.
• Monitor failures and ensure reliability and security.
• Speak with users to understand problems and design useful interfaces.
• Measure usage and impact of what you build.

Skills

React & TypeScript

PostgreSQL

APIs

Production systems

AI/LLM APIs

Data modelling

Education

Bachelors in CS

Tools

Supabase

Meta Marketing API

Job description

AI Automation & Full-Stack Product EngineerWhat if AI could do more than just write a caption?

Could it help launch and optimise ads?

Build landing pages?

Turn an idea into copy, static creatives and scripts?

Generate UGC-style content?

Automate reporting?

Answer internal questions?

Handle repetitive client communication?

Help our team make better decisions faster?

That’s what we want to find out and build.

CerealBox is looking for its first in-house AI Automation & Full-Stack Product Engineer: someone who can take a real business problem, figure out the smartest technical solution, build it, launch it, maintain it and continuously improve it as better AI models and tools become available.

This isn’t a role where someone gives you a list of tickets every morning.

You’ll be expected to ask:

“Why are we doing this manually?”

“Can AI solve this?”

“Should we build it ourselves or integrate an existing tool?”

“How do we make this 10x better?”

And then actually make it happen.

A little about CerealBox

We’re a UK-based creative and performance agency working exclusively with charities.

We manage digital fundraising and paid media for around 30 charity clients and have already built our own analytics platform, True ROAS, to connect advertising spend with actual donation revenue.

Now we want to take the next step.

We want AI and automation embedded across the business not because it sounds cool, but because it can genuinely help our team work smarter, move faster and deliver better results for charities.

Your first big responsibility

You’ll take ownership of True ROAS, our existing production platform used by our media buyers, creative team and leadership.

Today, it already handles:

• Attribution between Meta Ads and donation data
• ROAS reporting by client, campaign and creative
• Thousands of creatives and performance insights
• Commercial and settlement reporting
• Scheduled data syncs and API integrations
• Currency conversion and system monitoring

You’ll maintain it, improve it and help decide what it becomes next.

Then comes the fun part

Some of the problems we want you to explore include:

• AI Copywriting: Can AI consistently produce strong advertising copy?
• Creative Generation: Can static ad concepts and designs be automated?
• Script Writing: Can AI develop better hooks, concepts and video scripts?
• UGC: How much of UGC production can be generated using AI?
• Video Editing: Can AI take raw footage and produce high-quality finished ads?
• Media Buying: Can an AI agent help launch, monitor and optimise campaigns?
• Creative Ideation: Can AI generate genuinely interesting campaign concepts rather than generic ideas?
• Landing Pages: Can we rapidly generate and optimise fundraising landing pages?
• Reporting: Can reporting become almost completely automated?
• Internal AI Assistant: Can we make tools like Toast smarter so our team can simply ask questions and get useful answers?
• Client Communication: Can AI safely respond to common or repetitive queries?
• Workflow Automation: Can we remove repetitive operational work across the company?
• Meta + LLM Integrations: How can Meta data interact with models such as Claude and other LLMs?

You won't necessarily build every idea exactly as described.

Part of your job is deciding what is actually worth building.

What you’ll do AI & Automation

• Identify repetitive work that can be automated
• Research AI tools, APIs, models and agents
• Prototype solutions quickly
• Decide whether we should build, integrate or buy
• Turn successful experiments into reliable production tools
• Keep our AI systems current as models and technologies evolve

Full-Stack Engineering

• Build and maintain modern React and TypeScript applications
• Own backend architecture, APIs and database logic
• Work extensively with PostgreSQL and Supabase
• Build reliable third‑party integrations
• Maintain scheduled jobs and data pipelines
• Monitor failures and make sure systems are reliable and secure

Product & UX

• Speak directly with the people using your tools
• Understand the actual problem before writing code
• Design simple, useful interfaces
• Take features from rough idea → prototype → production
• Measure whether people actually use what you build
• Improve products based on real feedback

Our current stack

Frontend

React • Vite • TypeScript • TanStack Router & Query • Tailwind • shadcn/ui

Backend & Data

Supabase • PostgreSQL • Edge Functions • pg_cron • Row-Level Security

Hosting

Vercel

Integrations

Meta Marketing API • Fundraising platform APIs • AI/LLM APIs

Ways of working

GitHub • Pull Requests • AI-assisted development

And yes if you can show us that part of the stack should change, we’re open to the conversation.

We’d love to speak to you if you have

• 4+ years of professional software engineering experience
• Strong full-stack experience with React and TypeScript
• Solid PostgreSQL, data modelling and API experience
• Experience owning production systems
• Experience integrating third-party APIs
• Strong product thinking — not just coding from specifications
• The ability to design clean interfaces without waiting for perfect Figma files
• Confidence working independently and making technical decisions
• Curiosity around AI, automation, agents and LLM APIs
• Clear communication with non-technical teammates

Even better if you’ve worked with

• Supabase
• Meta Marketing API
• Performance marketing or ad-tech
• Marketing analytics
• Claude, OpenAI or other LLM APIs
• AI agents / tool calling / MCP
• Data visualisation
• Charity or fundraising technology
• Early‑stage products or agencies

You do not need to tick every single box.

If you’ve built real products, love figuring things out and can show us interesting things you’ve shipped, we’d still like to hear from you.

What you’ll get

A genuinely high‑ownership role

The freedom to experiment with AI and emerging technology

The opportunity to build products that are actually used every day

Exposure to an international UK‑based agency environment

Direct access to leadership and the people using what you build

Space to research, test and introduce better technology

21 days paid annual leave

Work that ultimately helps charities raise more money

What success looks like

We don’t simply want a longer codebase.

We want:

less repetitive work, better data, smarter tools, faster decisions and AI systems that genuinely make the CerealBox team better at what it does.

If reading this already has you thinking, “I know how I’d build that…” we should probably talk.

Apply with your CV, LinkedIn/GitHub profile and, most importantly, examples of products, automations or AI‑powered tools you’ve actually built.