Availability awaiting confirmation
We are waiting for a fresh update from the source. This page preserves the last received job details; current availability is not confirmed.
Job description
5 days ago Be among the first 25 applicants
Get AI-powered advice on this job and more exclusive features.
Project Overview
We are developing high-quality training and evaluation datasets to improve how Large Language Models (LLMs) perform on real software engineering problems. The core of this project involves identifying and curating verifiable coding tasks from public GitHub repositories, supported by a human-in-the-loop review process.
As a contractor on this project, you will review code written by AI to solve real software tasks. Your feedback will help improve how future AI models learn to write and understand code.
Key Responsibilities
Review and compare 3–4 model-generated code responses for each task using a structured ranking framework
Assess code changes (diffs) for correctness, quality, readability, and performance
Provide clear, concise explanations for your ranking decisions
Maintain consistency and fairness across all evaluations
Identify and document edge cases or unusual model behavior
Collaborate with the team to improve evaluation processes and identify improvement areas
Required Qualifications
Professional Experience
Several years of experience as a software engineer (experience working as a data scientist will not be considered)
Minimum 2 years of experience as a full-stack engineer at a leading tech product company (e.g., Google, Shopify, Microsoft, Snowflake, Meta, PayPal, etc.)
Note: Experience from contractual or part-time roles will not be considered. Only full-time employment qualifies.
Technical Skills
Strong understanding of software design, debugging, and engineering best practices
Familiarity with code review processes and version control systems
Ability to analyze and compare real-world code changes
Excellent written communication skills for clearly explaining technical evaluations
Preferred Qualifications
Degree from a top-ranked university is preferred but not required
Experience working with LLM-generated code or AI evaluation projects
Background in developer tools or systems automation
Exposure to AI research or developer agents
Type: Contract (no medical benefits or paid leave)
Commitment: 10–20 hours/week, with flexible work hours (partial overlap with Pacific Time)
Duration: 1 month (starting next week, with potential for extension)
Compensation: $50–$150/hour, based on experience, geography, and skill level
About Turing:
Turing is one of the world’s fastest-growing AI companies, pushing the boundaries of AI-assisted software development. Our mission is to empower the next generation of AI systems to reason about and work with real-world software repositories. You’ll be working at the intersection of software engineering, open-source ecosystems, and frontier AI.
If you have strong software engineering expertise and are interested in helping shape the next generation of AI-assisted development tools, we encourage you to apply.
#J-18808-Ljbffr
Worksite address
san francisco, CA, 94199, US
Who can apply
Review the original listing for work authorization, qualifications and employer requirements.