Senior Software Engineer – LLM Evaluation

By
Senior Software Engineer – LLM Evaluation Jobs at Turing | Are you an experienced software engineer with strong full-stack development, debugging, and software architecture skills? Turing is offering a contractor opportunity for senior software engineering professionals to help evaluate and improve advanced large language models (LLMs). This opportunity focuses on building coding datasets, reviewing AI-generated code, designing automated verification methods, and helping AI research teams develop more reliable software engineering systems. 📌 Job Overview - Job Title: Senior Software Engineer – LLM Evaluation - Company: Turing - Job Category: Software Development / Artificial Intelligence - Job Type: Contractor - Work Arrangement: Remote - Eligible Locations: United States, Canada, and specified Western European countries - Experience Required: 3+ years of software engineering experience - Referral Bonus: $1,000, subject to Turing's referral program terms - Weekly Commitment: Flexible, 10–40 hours - Contract Duration: 1 month, with potential extensions - Paid Leave: No medical or paid leave under the listed contractor arrangement - Application Time: Approximately 15–30 minutes - Evaluation Process: AI video interview required Important: This role is restricted to candidates based in the United States, Canada, or eligible Western European countries. Applicants in Pakistan should verify eligibility before applying. 📝 Job Description Turing works with leading AI research laboratories and global enterprises to improve the capabilities of advanced AI systems. For this project, Turing is seeking experienced software engineers to collaborate with AI researchers in creating datasets, evaluating coding performance, and improving the accuracy, efficiency, scalability, and reliability of AI-generated software. Successful candidates will apply their software engineering expertise to real-world development challenges and help establish methods for measuring and verifying AI coding capabilities. 🛠️ Key Responsibilities - Create and curate code examples for AI training and benchmarking. - Develop solutions and correct code across multiple programming languages. - Evaluate and refine AI-generated code for quality, efficiency, and reliability. - Collaborate with researchers and cross-functional teams on AI-driven coding solutions. - Build agents that assess code quality and identify recurring error patterns. - Evaluate AI capabilities across software development stages, including prototyping, architecture, API design, deployment, testing, and maintenance. - Design automated verification mechanisms to test software solutions. - Provide clear, structured explanations for technical evaluations. - Help improve the performance of AI systems on complex software engineering tasks. 🎯 Required Qualifications Applicants should have: - At least 3 years of professional software engineering experience. - Strong full-stack development skills. - Experience building and deploying scalable, production-grade applications. - A deep understanding of software architecture and design principles. - Strong debugging and code review capabilities. - The ability to assess code quality, correctness, and maintainability. - Excellent written and oral communication skills. - The ability to explain technical decisions clearly and systematically. 💻 Required Programming Languages The listing highlights the following programming languages and technologies: - Python - JavaScript, including ReactJS - Java - C and C++ - Rust - Go Experience across multiple languages and modern software development tools may help candidates demonstrate their technical expertise. 💼 Contract Details and Benefits Work Arrangement Remote contractor engagement Weekly Commitment Flexible, 10–40 hours per week Contract Duration 1 month, with possible extensions based on performance and fit Note: The supplied job description does not specify an hourly pay rate. Confirm compensation and final contract terms with Turing. 🧪 Application and Evaluation Process The application process takes approximately 15–30 minutes, and an AI video interview is required. Applicants should prepare to discuss their software engineering experience, technical problem-solving methods, code quality standards, and experience building production-grade applications. 🌍 Location and Eligibility Eligible candidates must be based in one of the specified regions: - United States - Canada - Eligible Western European countries, including Austria, Belgium, France, and Germany, among others Applicants based in Pakistan are not listed among the eligible locations. Check Turing's official job listing for the complete list of qualifying countries and any additional requirements. 📄 How to Apply 1. Prepare an updated CV highlighting your software engineering experience. 2. Include relevant full-stack development, architecture, debugging, and code review projects. 3. Highlight your programming language expertise and production deployment experience. 4. Confirm that your country of residence meets the role's location requirements. 5. Complete the application and required AI video interview. Apply Now