Skip to content

Coding

SWE Bench Engineer (Java LLM Code Evaluation)

Half of all Coding & Software Evaluation roles come down within 27 days of being listed, and 48.9% are still up after four weeks. This one was posted 5 days ago.

About the role

The work

You will assess Java software projects and help measure how well language models handle real bug-fixing tasks. The work involves running, changing, testing, and reviewing open-source code locally.

  • Analyze and triage issues in open-source Java libraries.
  • Set up repositories, Docker-based development environments, and basic software pipelines.
  • Review unit-test coverage and overall code quality.
  • Modify and run projects locally to evaluate LLM performance on bug-fixing tasks.
  • Find repositories and issues that create meaningful evaluation challenges for language models.
  • Work with researchers and, when needed, guide junior engineers on related projects.

What it pays and takes

This is a remote contractor assignment for freelancers in Latin America. It is a one-month contract, and the structured time commitment is 20 or more hours per week.

  • Pay: $25 per approved task.
  • Location: Open to candidates in Latin America.
  • Schedule: 20 or more hours per week, including four hours of overlap with PST.
  • Experience: At least three years of overall software engineering experience.
  • Technical skills: Strong hands-on Java experience, plus proficiency with Git, Docker, and basic software pipeline setup.
  • You must be comfortable navigating complex codebases and running, modifying, and testing real-world projects locally.
  • Helpful experience includes contributing to or evaluating open-source projects, participating in LLM research or evaluation, and building or testing developer tools or automation agents.
  • Language: Professional fluency in English.

How it works

Apply on OpenTrain with your resume, then complete the application on the hiring site.

About AI training work

AI training work uses human review to help improve artificial intelligence systems. In this role, software engineers evaluate model-generated code and realistic bug-fixing attempts, so strong engineering experience helps produce reliable feedback.

Where you can work

This role is 100% remote, for applicants located in these 16 countries: Argentina, Bolivia, Chile, Colombia, Costa Rica, Dominican Republic, Ecuador, Guatemala, Guyana, Mexico, Panama, Peru, Puerto Rico, Paraguay, El Salvador and Uruguay.

From OpenTrain AI's job posting, checked 16 Nov 2026.

About OpenTrain AI

A unified board of AI-training jobs with real per-role pay.

How it pays: Stripe payouts to your bank, in the 120 countries its payout docs list.

When it pays: When the employer approves each funded milestone. How often others pay

Interview: on some roles or projects (AI interview (switched on per job by the employer)). How the OpenTrain AI AI interview works

Similar open roles

Some links on AITraining.jobs are referral links. If you sign up through one, AITraining.jobs may earn a commission at no extra cost to you. It never changes what a platform pays you. A role at a platform that pays us a referral fee weighs more in this order.

An experienced engineer?

One profile for every AI training platform. Companies ask us for people with a specific language, country or credential: add yours once, and when a role fits, we introduce you, only with your yes. Free.

Create my profile

Get new OpenTrain AI roles by email

We check the OpenTrain AI job board every hour and email you its newest roles each week, plus similar paid roles elsewhere. Free, unsubscribe anytime.