Research Engineer, Coding Evaluation & Training Data

Overview

Surge is hiring a Research Engineer, Coding Evaluation & Training Data to help build and run systems that teach frontier models how to code. This role sits at the intersection of software engineering and product, with a focus on training data quality, agentic evaluation, and system design for top AI labs.

The work centers on creating coding data projects that reflect real-world software engineering, including RL environments, evaluation schemes, and workflows used to assess and improve model coding capabilities.

What You'll Do

• Own coding data projects end to end, 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 measure true engineering value beyond simple compilation success.
• Review data and worker output with strong engineering judgment and decide what meets the standard 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, repositories, test harnesses, sandboxes, and code execution infrastructure.
• Work with technical staff at client companies 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 programming language and comfort working in production codebases.
• Strong judgment for good engineering practices, including correctness, code quality, and how real teams work.
• 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.
• Interest in AI/ML systems and in how data, evaluation, and reward design improve agentic coding capabilities.