Website:
codevalid.io
Job details:
We’re looking for an AI Engineer to join us at CodeValid, working on a problem we think is quietly becoming critical: how do you trust code generated by AI?
As AI-assisted coding accelerates development, testing and validation are lagging behind. We’re building systems that bridge that gap, turning specs into reliable, testable code with confidence.
This role is for someone who enjoys building at the intersection of:
- AI agents / autonomous workflows
- Software engineering fundamentals
- Test-driven development (TDD) and quality systems
What you’ll work on
- Build agents that generate and validate tests from product specs
- Design workflows that connect intent → code → verification
- Improve reliability of LLM outputs through testing and feedback loops
- Work closely on developer tooling and CI-like validation systems
What we’re looking for
- Strong software engineering background (Python/TypeScript preferred)
- Experience building or experimenting with AI agents / LLM-based systems
- Solid understanding of testing practices (TDD, unit/integration testing)
- Ability to think in systems — not just prompts, but workflows
- Bonus: experience with developer tools, compilers, static analysis, or codegen
Why this might be interesting
- You’ll be working on a problem that sits at the core of the AI + software shift
- Small team, high ownership, fast iteration
- Opportunity to shape how trust in AI-generated code is built
- We’re early, curious, and moving fast — not overly polished, but focused on building something meaningful.
Click on Apply to know more.