Remote C# Developer for LLM Evaluation Projects

About the role

We are seeking an experienced C# developer to join our AI team and help build large‑language‑model (LLM) evaluation datasets. You will work remotely, collaborating with researchers and engineers to create realistic software‑engineering tasks from public GitHub repositories.

Key responsibilities

• Analyze and triage issues in trending open‑source libraries on GitHub.
• Set up and automate code repositories, including Dockerization and environment configuration.
• Evaluate unit‑test coverage and overall code quality.
• Run, modify, and test codebases locally to assess LLM performance in bug‑fixing scenarios.
• Partner with researchers to select challenging repositories and design evaluation tasks.
• Optionally lead junior engineers on project components.

Required profile

• Minimum 3 + years of professional software‑engineering experience.
• Tech‑lead level competence with complex codebases.
• Familiarity with high‑quality public GitHub repositories.
• Ability to work at least 20 hours per week with a 4‑hour overlap in PST.

Required skills

• C# programming language.
• Git version control.
• Docker containerization.
• GitHub repository navigation.
• Running and testing real‑world projects locally.

What we offer

• Fully remote, flexible work schedule.
• Opportunity to influence cutting‑edge AI research on software development.
• Collaboration with leading LLM companies.
• Freelance contract (no medical or paid leave).