Senior Software Engineer – C# (LLM Evaluation & Repository Validation)

The rapid evolution of artificial intelligence has moved past simple text generation; today's frontier models must reason through complex, production-grade software engineering challenges. Training Large Language Models (LLMs) to understand and write functional code requires expertly curated datasets derived from real-world repository histories.

Turing—one of the world's fastest-growing AI companies accelerating the advancement of intelligent systems—is engaging senior software engineers for a specialized remote contractor role focused on C# LLM Evaluation and Repository Validation.

About the Projects & Role

This initiative builds verifiable Software Engineering (SWE) tasks based on public repository histories using a synthetic approach with a human-in-the-loop. You will expand dataset coverage across programming languages, difficulty levels, and domain scenarios.

As a tech-lead level engineer, your work involves hands-on development environment automation, issue triaging, and evaluating test coverage and quality to ensure AI models can autonomously handle complex debugging and code synthesis.

Are You a Fit? Required Skills & Experience

To succeed in this engagement, candidates must demonstrate robust technical competence and professional experience:

• Minimum 3+ years of overall software engineering experience.
• Strong, production-level experience with C#.
• Proficiency with Git, Docker, and basic software pipeline setup.
• Ability to understand, navigate, and modify complex codebases.
• Comfort running, modifying, and testing real-world projects locally.
• Nice to Have: Prior participation in LLM research, experience building developer tools/automation agents, or open-source contributions.

Engagement Details & Flexibility

This is a remote contractor role designed for elite global engineering talent. Time commitment options include 20 hours, 30 hours, or 40 hours per week (requiring at least 4 hours per day and a 4-hour overlap with PST).

Interview Process & Onboarding Roadmap

The evaluation process takes approximately 75 minutes, consisting of two rounds:

1. Technical Round (60 minutes): Deep dive into coding, architecture, and problem-solving.
2. Technical & Cultural Discussion (30 minutes): Alignment on project standards and collaboration.

Upon selection, completing your onboarding and finishing your first 10 hours of work is crucial. This initial milestone ensures workflow stability, validates your setup, and unlocks access to broader, higher-volume tasks within the Turing network.