Senior Software Engineer AI Evaluation Remote Job | $100–$150/hr | Turing
Senior Software Engineer – AI Evaluation / Coding Agents | Remote Job at Turing
Company: Turing
Position: Senior Software Engineer – AI Evaluation / Coding Agents
Job Category: Software Development / Artificial Intelligence
Engagement Type: Independent Contractor / Freelance
Location: Remote – North America Only
Compensation: $100–$150 per hour
Project Duration: Approximately 3 months
Availability: 20–40 hours per week
Time-Zone Requirement: At least 6 hours of Pacific Time overlap per day
Start Date: As soon as possible
About Turing
Turing is an AI infrastructure company working with leading AI research organizations to accelerate model development through high-quality training data, evaluations, and engineering expertise.
Role Overview
Turing is seeking experienced software engineers to evaluate and improve AI coding models. In this role, you will work with AI coding agents across real-world software repositories and assess the quality, accuracy, and reliability of their code.
You will review AI-generated implementations, identify technical issues and failure points, evaluate engineering decisions, and provide feedback that helps improve AI model performance.
The focus is on evaluating AI-generated code rather than primarily building production applications.
Project and Compensation Details
- Hourly Rate: $100–$150 per hour.
- Rate Expectation: Applicants must provide a specific hourly rate expectation.
- Workload: 20–40 hours per week.
- Availability: At least 6 hours of overlap with Pacific Time each day.
- Duration: Approximately 3 months.
- Work Arrangement: Fully remote freelance contractor engagement.
- Location Eligibility: North America only.
- Start: As soon as possible.
Key Responsibilities
- Evaluate AI-generated code across real-world software repositories.
- Assess whether coding agents understand tasks and select appropriate technical solutions.
- Review code for correctness, reliability, robustness, and maintainability.
- Design, refine, and improve evaluation rubrics and criteria for preference data.
- Review and label data while identifying subtle technical issues.
- Build and maintain pipelines and infrastructure for data generation, collection, and evaluation workflows.
- Prepare clear technical reports, updates, findings, and recommendations.
- Collaborate with researchers and engineers to turn technical judgments into scalable evaluation processes.
Mandatory Qualifications
- At least 5 years of hands-on software engineering experience.
- Strong proficiency in Python, TypeScript, JavaScript, Go, or another major production programming language.
- Experience working with substantial real-world codebases.
- Strong code-review skills and technical judgment.
- Ability to explain clearly why an implementation is correct, incorrect, or needs improvement.
- Strong written communication skills.
- Experience using modern LLMs or AI coding tools.
Required and Relevant Technical Skills
- Python
- TypeScript and JavaScript
- Go or Java
- GitHub
- CI/CD workflows
- Open-source software
- Large Language Models (LLMs)
- Code reviews and code analysis
- AI coding tools and coding agents
Preferred Experience
The following experience is an advantage but is not mandatory:
- LLM evaluation
- AI coding agent evaluation
- Reinforcement Learning from Human Feedback (RLHF)
- Preference data creation and review
- Evaluation rubric design
- AI model post-training
Evaluation and Interview Process
- AI Interview: Approximately 25 minutes.
- Practical Code / AI Evaluation Exercise: Approximately 30 minutes.
- Hiring Manager Interview: Approximately 20 minutes.
Important: The practical exercise focuses on reviewing and evaluating AI-generated code. It is not a competitive programming test or an algorithm puzzle challenge.
Who Should Apply?
This opportunity is suitable for senior software engineers with at least five years of professional development experience, strong code-review abilities, and familiarity with modern AI coding tools.
Applicants must also meet the North America location requirement and be available for the required Pacific Time overlap.
How to Apply
Visit Turing's official website to explore opportunities and confirm the application process for this specific project.
Note: The specific application link was not included in the supplied job description. Confirm the correct application link with the recruiter or authorized source.
Important Eligibility Notes
- This role is open to applicants in North America only.
- Minimum 5 years of software engineering experience is required.
- Applicants must provide a specific hourly rate expectation within the advertised $100–$150 range.
- Availability of 20–40 hours per week is required.
- At least 6 hours of Pacific Time overlap per day is required.
- This is an approximately 3-month independent contractor engagement, not a permanent employment guarantee.
AQZORA Jobs
Discover Global Remote Jobs & Career Opportunities
Explore remote software jobs, AI projects, technology opportunities, and international careers.