Skip to content
Labeling Jobs

Senior Software Engineer: LLM Evaluation (US/Canada/WEU based)

Pay
Pay not stated
Open to
Worldwide
Apply

We earn a commission if you sign up through the links on this page. It costs you nothing and does not affect which jobs we list. How this works.

Skills
  • python
  • javascript
  • java
  • c++
  • rust
  • code review

What you'll do

This is the broadest of Turing's software engineering evaluation roles in this set: not one language, not one repository, but the whole software lifecycle as seen by a language model. You work with researchers to produce datasets that train and benchmark models, and you judge model output as an experienced reviewer would.

  • Curate code examples, write solutions and correct code in Python, JavaScript (including ReactJS), C/C++, Java, Rust and Go
  • Evaluate and refine AI-generated code for efficiency, scalability and reliability
  • Build agents that check code quality and spot error patterns
  • Form hypotheses about stages of the engineering cycle (prototyping, architecture, API design, production implementation, launch, experiments, monitoring, maintenance) and test how well models handle each
  • Design verification mechanisms that can automatically check a solution to an engineering task

Who fits

  • 3 or more years of software engineering experience
  • Strong full-stack skills and experience deploying scalable, production-grade software
  • Deep understanding of architecture, design, debugging and code review
  • Clear written and spoken communication, since you write structured rationales for evaluations

What it pays

The ad does not publish a rate. Turing sets rates per project; see Turing.

Commitment and location

  • Flexible: a minimum of 10 hours a week, up to 40
  • Contractor (no medical or paid leave)
  • Duration: 1 month, with possible extensions based on performance and fit
  • Location: candidates must be based in the US, Canada or Western Europe. The ad names Austria, Belgium, France, Germany and then trails off, so check the full country list on the application page

Worth knowing

Good:

  • Low minimum of 10 hours a week, so it can sit alongside another job
  • No time zone overlap requirement is stated
  • The scope includes designing verifiers, which is more creative than reviewing alone

Less good:

  • No rate published
  • Only one month is guaranteed; extensions depend on performance
  • Restricted to the US, Canada and Western Europe
  • Needs an AI video interview as part of applying

How hiring works

The ad says the application takes 15 to 30 minutes and requires completing an AI video interview.

About this listing

Read from Turing's job board on 18 October 2026. First posted in November 2025. See Turing.

More roles at Turing

See all 118

Similar roles at other platforms

Browse similar roles

Not the right fit?

See every open role, or get new ones on Telegram or Discord as they are added.