Continuum Resource Network
Software Engineer - Technical Advisor
United States · Remote · Full-time · Posted Aug 27, 2026
- Experience
- 8+ years of production engineering experience; exceptions only for clearly exceptional profiles.
About the job
Evaluates AI coding agents and model-generated code against production engineering work, and builds challenging benchmarks to identify model failures.
What you'll do
- Analyze AI coding-agent sessions and document their investigation, verification, assumptions, and omissions.
- Review model-generated pull requests in production repositories, recording issues, severity, and technical rationale.
- Build container-based evaluation benchmarks and collaborate with AI researchers on failure analyses.
What they ask for
- 8+ years of production engineering experience; exceptions only for clearly exceptional profiles.
- Experience in production codebases with a strict code review culture.
- Comfort using Docker, git, and the Command Line Interface (CLI) to reproduce, isolate, and debug results locally.
- Cross-layer engineering fluency and strong written communication skills.
Nice to have
- Background as a Senior, Staff, or Principal Software Engineer, Tech Lead, or Open-Source Maintainer.
- Heavy experience with Python and TypeScript; adaptability to unfamiliar languages.
Tools
Python, TypeScript, Docker, git, Command Line Interface (CLI)
AI focus
Evaluate frontier AI coding agents and model-generated pull requests, build benchmarks for frontier models, and analyze model failures with AI researchers. AI tools are welcomed for codebase exploration and running test suites; written deliverables must be independently authored without AI text generation.
Model-written summary · the original posting is authoritative