Senior Software Engineer – Rust (LLM Evaluation & Repository Validation)

Location: Permanent Remote, Africa-Based
Contract Type: Contractor (no medical/paid leave)
Duration: 3 months (extensions possible)
Start Date: Immediate (within 1 week)
Commitment: 20–40 hours/week with some overlap with Pacific Standard Time (PST)
Experience Required: 3–8 years overall, with 2+ years in Rust

About the Project

We are building LLM evaluation and training datasets to train large language models (LLMs) to work on realistic software engineering problems. A key approach in this project involves creating verifiable SWE tasks from public repository histories in a synthetic, human-in-the-loop process. The goal is to expand dataset coverage across programming languages, complexity levels, and problem domains.

This role blends hands-on software engineering with AI-focused research, giving you a chance to work at the intersection of open-source software and cutting-edge AI systems.

Responsibilities:

• Analyse and triage GitHub issues across trending open-source libraries.
• Set up and configure repositories (including Dockerization and development environment setup).
• Evaluate unit test coverage and quality across projects.
• Run and modify codebases locally to assess LLM bug-fixing performance.
• Collaborate with researchers to design/select repositories and tasks challenging for LLMs.
• (Optional) Lead junior engineers collaborating on evaluation tasks.

Must-Have Skills:

• 3–8 years of professional software development experience.
• Minimum 2+ years of experience with Rust in production environments.
• Strong proficiency with Git, Docker, and software pipelines.
• Ability to navigate and understand complex, real-world codebases.
• Comfortable running, modifying, and testing repositories locally.

Nice-to-Have Skills:

• Prior contributions to or evaluation of open-source projects.
• Experience with developer tools, automation agents, or AI/LLM evaluation.
• Exposure to LLM-related research or dataset generation.

Why Join:

• Work remotely on impactful AI + software engineering projects.
• Collaborate with researchers shaping the future of AI-assisted development.
• Opportunity to contribute to real-world open-source challenges while influencing LLM training and evaluation.

Application Process: To apply, please submit your CV and a cover letter detailing your relevant experience and qualifications for the role. Applications will be reviewed on a rolling basis, so early submissions are encouraged.

Equal Opportunity Employer: We value diversity and are committed to creating an inclusive work environment. We encourage applicants from all backgrounds to apply.

Contact: Elvis Eckardt