Experts / Train AI / Coding

Engineers who train coding models.

Software engineers who write, review and test code tasks and agent runs for frontier models.

What software engineers do.

Each one writes production code for a living and is AI-interviewed in their stack.

  1. Write

    Realistic coding tasks with reference solutions and tests.

  2. Review

    Rank and correct model code on correctness and style.

  3. Verify

    Run agent trajectories and check results with tests.

  4. Red-team

    Find insecure or broken code before your users do.

Specialities: Python · TypeScript · Java · Go · Rust · C++ · SQL · Infrastructure

Sample coding tasks.

Multi-step tasks, checked end to end

An engineer writes a realistic task in a real repository, runs the agent, and verifies the result with tests rather than by eye.

  • Tasks built in real environments
  • Pass/fail checked by tests
  • Trajectory reviewed step by step

Questions

Anything else? Talk to us and a specialist will reply.

How do you check software engineers' expertise?

Each expert passes a 10-minute AI interview in coding, and a senior expert in the same field reviews their score before they work on any task.

Can we choose the sub-specialities and languages?

Yes. Tell us the sub-specialities, languages and countries you need, and we recruit and calibrate experts to match before the pilot.

How is our data protected?

Project data stays in an isolated workspace, is encrypted at rest and in transit, and is never used to train other models.

I work in coding. How do I join?

Apply with the short form on our Find work page. You take one AI interview in coding, and we match you to projects that fit your expertise and hours.

How much does the work pay?

Rates depend on the project and your level. You see the rate before you accept any work.

For companies and labs

Request coding data.

Request a sample

For experts

Train coding AI.

Apply now