Intelligent Systems Company in London seeks a research-driven engineer to design and build a unified benchmark evaluation system for agentic and algorithmic AI workloads. You will mine real commits and traces, run sandboxed grading, enforce contamination controls, and publish co-authored benchmark results that inform shipping decisions.
This research-into-production role requires strong Python, distributed execution, and experience with code-agent tasks. London office-based role.
#J-18808-Ljbffr
AI Benchmarking Architect - Research Engineer in London employer: United States Digital Space LLC
At our company, we pride ourselves on being an exceptional employer, offering a vibrant work culture that champions diversity and inclusion. With a strong focus on employee growth, we provide clear career paths, personal learning budgets, and generous benefits such as private healthcare and a flexible work-from-abroad policy. Join us in London and be part of a team dedicated to making a positive impact through greener travel choices while enjoying the perks of a supportive and innovative environment.
Contact Details:
United States Digital Space LLC Recruitment Team