Research Engineer, Coding Evaluation & Training Data

📋 Description

• Own end-to-end coding data projects from scope to scale-up.
• Design agentic training workflows mirroring real-world SWE work.
• Define rubrics, golden sets, and reward signals capturing true engineering value.
• Evaluate data and worker output with strong SWE taste.
• Design and run qualification processes for coding workers (hands-on).
• Set up complex technical environments (containers, repos, test harnesses, sandboxes).

🎯 Requirements

• 3–6+ years of professional software engineering experience.
• Strong coding ability in at least one mainstream language and production codebases.
• High “taste” for good engineering: correctness, code quality, and practical workflows.
• Ability to reason about and debug technical environments, including containers, dependencies, and automated test setups.
• Excellent written and verbal communication skills, with the ability to translate fuzzy goals into actionable plans.
• Excitement about AI/ML systems and the role of data, evaluation, and reward design in improving agentic coding capabilities.