Full Stack Software Engineer

Duku AI; Cape Town; On-site; ZAR 600,000 - 900,000; Full time

Job summary

Duku AI in Cape Town is seeking a Full Stack Software Engineer to create trusted AI solutions. In this role, you will deploy daily, work closely with founders to shape the product, and help train AI agents for automated testing.

Ideal candidates will have experience in shipping AI features and thrive in fast-paced environments. Join us to redefine software delivery with our innovative autonomous testing methods.

Qualifications

• Experience shipping AI features in production.
• Ability to thrive in chaotic startup environments.
• Strong commitment to product outcomes.

Responsibilities

• Deploy daily and adapt quickly to new challenges.
• Collaborate with founders to define the product roadmap.
• Design and train AI agents for automated testing.
• Manage the full stack from development to production.
• Convert prototypes into real-world applications.

Skills

Fluency with AI/LLMs

Relentless drive

Startup experience

Tools

Python

TypeScript

Cloud infrastructure

Job description

Most engineering roles build software nobody fully trusts. This one builds the trust layer itself. AI is making engineers dramatically more productive. The problem is nobody fully trusts what AI ships.

Why this matters now

AI is rewriting how software gets built. But shipping still breaks on testing. Engineering leaders are desperate to release faster without dropping quality, and they can't get there with manual QA or brittle test automation.

Here's the bigger shift: as AI writes more of the code, the bottleneck moves from generating software to trusting it. Nobody owns that trust layer yet. Duku is building it, autonomous agents that simulate real users, catch critical failures before production, and self-heal as the product evolves.

Backed by experienced operators and investors, we're building what we believe will become a core layer of the modern software stack. We're looking for an exceptional Full Stack Software Engineer to help build it. Not someone to maintain a codebase. Someone to define one.

What You’ll Do

• Ship fast, learn faster : We deploy daily, not monthly
• Talk to users, shape the roadmap : Sit in the trenches with founders on calls that define what we build
• Train AI agents: Design LLM-powered testers that explore, learn, and adapt in real time
• Own the stack :Python, TypeScript, cloud infra, from commit to production
• Turn prototypes into production : Run real experiments on models, embeddings, and retrieval pipelines

What We’re Looking For

• Relentless drive: You execute fast, adapt faster
• Startup scar tissue : You’ve shipped product with no safety net
• Fluency with AI/LLMs : LangChain, vector stores, prompt engineering
• Product obsession : You care more about outcomes than outputs

Ideal Background

There's no perfect pedigree. We hire for mindset, not credentials. That said, you might have:

• Shipped AI features in prod
• Built something from 0 to 1
• Thrived in chaos with high ownership

Why This Matters

Software is accelerating. QA hasn't kept up. Autonomous testing is inevitable, and we're building it.

Five years from now, every high-velocity team will rely on AI agents like ours to ship faster, safer, and smarter.

Join now, and help make that future real, before someone else does.