17 nov
|
OpenTrain AI
|
Argentina
17 nov
OpenTrain AI
Argentina
You will evaluate open-source software repositories and examine how well large language models handle real bug-fixing tasks. The work combines software engineering, test review, environment setup, and hands-on code evaluation.
You will work with public GitHub repositories and collaborate with researchers to find issues and projects that are difficult for AI systems to solve.
- Analyze and triage issues in open-source libraries.
- Configure repositories and development environments, including Docker-based setups.
- Review unit-test coverage and overall test quality.
- Run, modify, and test real-world C# codebases locally.
- Evaluate LLM performance on software bug-fixing tasks.
- Help identify repositories and issues that challenge AI systems.
Requirements
This is a remote contractor assignment open to professionals in Latin America. The contract lasts four weeks, and the work includes four hours of overlap with Pacific Time.
- Time: 20+ hours per week.
- Experience: At least three years of software engineering experience.
- Technical skills: Strong C# or C++ experience, Git, Docker, and basic software pipeline setup.
- You must be able to run, modify, and test real-world projects locally.
- LLM research, evaluation, developer tools, or automation-agent experience is an advantage.
- Skills: C#, C++
Open to applicants in
- Argentina
- Belize
- Bolivia
- Chile
- Colombia
- Costa Rica
- Dominican Republic
- Guatemala
- Honduras
- Mexico
- Panama
- Paraguay
- Uruguay
Preferred
- Experience contributing to or evaluating open-source projects is helpful.
Complete coding-heavy AI training tasks involving machine learning models, Python, evaluation systems, and performance optimization. Work remotely for about 15 hours per week, with $60 to $120 per hour equivalent, paid per accepted task.
Create realistic bugs, features, refactoring, and performance tasks that test AI coding ability. This part-time contractor role pays $50 to $100 per hour equivalent, paid per task that meets project specifications.
Python3 JAVA Rust Algorithms Basics C++ Typescript
Work remotely on AI training projects involving Godot game development, gameplay systems, and technical reviews. Earn $70 to $130 per hour with versátil weekly hours over 1 to 3 months.
Build multi-step AI agents for mathematical research, turning proofs and technical material into reliable software systems. This remote contractor role is open across Latin America and pays $25 per approved task.
Evaluate AI coding tasks using real repository code, technical rubrics, and clear written feedback. The role pays $50 to $100 per hour equivalent, paid per task that meets the project specifications, for about 15 hours per week.
Python3 JAVA Rust Algorithms Basics C++ Typescript
📌 SWE Bench Engineer C# Code Evaluation (Argentina)
🏢 OpenTrain AI
📍 Argentina