QA Software Test Engineer Code Review - Remote
YO IT Consulting
See how well this job matches your profile
Sign up to get an AI match score and generate a tailored application in seconds.
Get your match scoreTags
About the role
Role Overview
QA Software Test Engineer (Code Review) — Remote
You’ll work as an independent contractor to help build code-focused evaluation datasets used by AI research teams to assess reasoning, explanation quality, and technical judgment in coding-related interactions. Tasks are structured as chat-pasteable prompts with all necessary context inline (code snippets, error messages, logs, and requirements).
Responsibilities
- Craft realistic developer prompts across categories such as:
- Code review
- Debugging
- Error diagnosis
- Configuration
- Others relevant to coding workflows
- Source and adapt scenarios from real PRs to create authentic dataset examples
- Write clear, technically accurate model responses demonstrating strong reasoning and explanation quality
Requirements
- 2+ years of experience in software engineering, technical research, or educational content development
- Bachelor’s minimum in Software Engineering, Computer Science, or a related field (advanced degree preferred)
- Strong proficiency in one or more of: Python, JavaScript, Java, C++
- Experience with debugging, testing, and validating code
- Comfortable with technical writing and strong attention to detail
Contract Details
- Independent contractor
- Fully remote (on your own schedule)
- Start: Immediate
- Duration: 1–2 months (may be extended/shortened based on needs and performance)
- Commitment: Part-time 15–25 hours/week, flexibility up to 40 hours/week
Hiring Process
- Resume upload
- Short 15-minute conversational AI interview
- Follow-up communication with next steps and onboarding details
About YO IT Consulting
YO IT Consulting is an IT consulting firm that supports high-impact research collaborations, including work with leading AI labs. The engagement described focuses on building evaluation datasets and materials used to assess AI reasoning and code-related capabilities.
Scraped 4/7/2026