Back
Remote, generalist Software Engineer title, mid-level (3+ years), and known startup brand create high applicant competition.
C++ specialization and open-source triage focus moderately limit cross-industry transferability.
Explicit 3+ years, required C++, Git/Docker, and PST overlap produce moderate filtering.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Lead hands-on software engineering efforts to develop and automate environments for LLM evaluation on public GitHub repositories.
Analyze and triage issues across open-source codebases, evaluate unit test coverage and quality, and modify code locally to assess LLM bug-fixing performance.
Collaborate with researchers and potentially lead junior engineers to enhance datasets and challenges for LLMs on complex software tasks.
Minimum 3+ years overall software engineering experience.
Strong proficiency in C++.
Experience with Git, Docker, and software pipeline setup.
Ability to understand, navigate, and modify complex real-world codebases locally.
Experienced with public/high-quality GitHub repositories and open-source project workflows.
Prepared to work in a remote contractor role with flexible weekly hours and some PST time overlap.
Capable of bridging practical software engineering with AI research needs, especially LLM evaluation tasks.