Machine Learning Systems Engineer

To support AI Safety and Security Engineering initiatives, the full-time Evaluation and ML Systems Engineer will design evaluation infrastructure, define metrics and protocols, and ensure traceability of results, working remotely or onsite in select locations. Key responsibilities: Build the benchmarking and reproducibility systems necessary for evaluation Define metrics and protocols for measuring performance Map results to the code and runs that produced them to ensure traceability Required qualifications: Bachelor's degree (or equivalent experience) with 5+ years in ML engineering or evaluation Experience designing benchmarks, metrics, and statistically sound comparisons for ML systems Demonstrated measurement rigor with a careful approach to metrics and claims Strong Python engineering skills for developing shared infrastructure