Research Engineer, Coding Evaluation & Training Data

Overview

Surge AI is seeking a Research Engineer, Coding Evaluation & Training Data to build and run systems that help frontier models learn to code. This role sits at the intersection of software engineering and product, with ownership over end-to-end coding data projects for top AI labs.

The work focuses on designing realistic tasks, RL environments, and evaluation schemes that reflect real software engineering, with an emphasis on training data quality, agentic evaluation, and system design rather than traditional product feature development.

What You'll Do

• Own coding data projects from scoping and pilot design through execution, iteration, and scale-up.
• Design agentic training workflows and task structures that mirror real SWE work such as refactoring, debugging, code review, large-repo navigation, and tool use.
• Define and refine rubrics, golden sets, and reward signals that capture real engineering value.
• Evaluate data and worker output with strong software engineering judgment and decide what meets the bar for frontier training.
• Design and run qualification processes for coding workers, including hands-on assessments of coding ability.
• Set up or partner on technical environments such as containers, repos, test harnesses, sandboxes, and code execution infrastructure.
• Work with technical staff at client organizations to turn high-level training goals into concrete projects and environments.
• Collaborate with Surge engineering, product, and operations to improve coding data products, internal tools, and execution processes.

What We're Looking For

• 3–6+ years of professional software engineering experience building and maintaining real systems.
• Strong coding ability in at least one mainstream language and comfort working in production codebases.
• Strong engineering judgment focused on correctness, code quality, and how real engineering teams operate.
• Ability to reason about and debug technical environments, including containers, dependencies, and automated test setups.
• Interest in owning projects end to end, including scoping, workflow design, execution, and continuous improvement.
• Excellent written and verbal communication skills, including the ability to speak credibly with senior client engineers and 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.