Research Engineer, Coding Agents

About Turing

Turing builds large-scale datasets and reinforcement learning (RL) environments that power post-training for the world's leading AI labs and enterprises, including OpenAI, Anthropic, Google DeepMind, Microsoft AI, Amazon, Apple, and many more. We create RL environments to evaluate and improve our customers' models on complex, multi-step workflows across high-value domains — designing the tasks, reward signals, and verifiers that drive measurable model improvement through RL training.

The Role We are looking for a

Research Engineer, Coding Agents

to help deliver frontier-quality datasets, RL environments, and evaluations that improve state-of-the-art coding models and software engineering agents for leading AI labs and enterprise clients. This is a hands-on, research-facing technical role. You will work directly with customer researchers and engineers to turn their coding agent improvement goals into concrete data and environment specs — designing tasks that reflect real software engineering work and building the ground-truth systems that verify agent performance.

We're targeting candidates with roughly 4–5 years of experience, ideally combining strong software engineering fundamentals with exposure to ML/AI systems — especially where results depended on data quality, evaluation rigor, or building infrastructure that other engineers rely on.

What You'll Do: 1. Design and deliver datasets and RL environments for coding agents Work with customer researchers to define data requirements for coding agent capabilities: codebase navigation, bug localization, patching, test generation, code reviews, CI-like constraints, refactors, and security fixes. Design task suites that reflect real development work — single-step tasks (fix this bug, write this test) through long-horizon workflows (navigate an unfamiliar repo, diagnose a multi-file issue, produce a reviewed PR). Build ground-truth signals: unit tests, structured checks, automatic validators, and reward functions that verify whether an agent's code actually works. Define environment interfaces — repository structures, dependency contexts, tool schemas — that give agents realistic constraints.

2. Build the quality and validation systems that ensure frontier-grade data Perform deep, detail-oriented audits of produced data — spotting subtle errors, reward hacking opportunities (e.g., agents gaming test suites), leakage, and inconsistent assumptions. Implement automated validation and filtering: deduplication, decontamination, consistency checks, and difficulty/diversity controls. Where appropriate, develop synthetic task generation pipelines: programmatic bug injection, controlled perturbations to existing codebases, and scenario templating across languages and frameworks.

3. Prove impact through evaluations and training runs Design and run evals aligned with coding benchmarks and customer-defined capability targets. Produce analysis connecting data to outcomes: pre/post comparisons on targeted coding tasks, error breakdowns, and ablations identifying which data attributes drive model lift on SWE tasks. When needed, run fine-tuning or RL experiments (or partner with research) to demonstrate measurable coding agent improvement.

4. Collaborate with cross-functional delivery teams Provide clear specs, examples, and edge cases to engineers, QAs, and large-scale data production groups. Run fast feedback loops grounded in code quality metrics and automated signals. Review and improve outputs from large-scale task creation efforts, maintaining a high bar for realism and correctness.

Who We're Looking For: 1. Required Qualifications 4–5 years of professional software engineering or ML engineering experience. Python proficiency required; proficiency in one or more additional major languages (C++, Java, Go, Rust, JS/TS) strongly preferred. Strong intuition for what makes a good coding task — realistic difficulty, clear ground truth, and resistance to shortcut solutions. Demonstrated ability to be extremely detail-oriented: you catch bugs in code that automated tools miss. Experience with testing infrastructure, CI/CD, or code quality systems at a meaningful scale. Ability to communicate clearly with researchers and engineers — turning model improvement goals into concrete task specs.

2. Highly valued experience Experience building or evaluating coding agents, copilot systems, or AI-assisted development tools. Familiarity with coding benchmarks (SWE-Bench, HumanEval, or equivalent). RL or post-training work: RLHF, reward modeling, verifier training, or environment design. Experience designing or maintaining evaluation harnesses for ML systems. Comfort with SQL and structured data workflows

Why Turing Work directly with the world's leading AI labs on the RL environments powering post-training for frontier models. Real impact: your environments and reward systems will directly shape how models learn to reason, act, and improve. Talent-dense team with high autonomy, rapid iteration, and an exceptional learning curve.

Values: We are client first

: We put our clients at the center of everything we do, because their success is the ultimate measure of our value. We work at Start-Up Speed:

We move fast, stay agile and favor action because momentum is the foundation of perfection We are Al forward:

We help our clients build the future of Al and implement it in our own roles and workflow to amplify productivity.

Advantages of joining Turing: Amazing work culture (Super collaborative & supportive work environment; 5 days a week) Awesome colleagues (Surround yourself with top talent from Meta, Google, LinkedIn etc. as well as people with deep startup experience) Competitive compensation Flexible working hours

Don’t meet every single requirement? Studies have shown that women and people of color are less likely to apply to jobs unless they meet every single qualification. Turing is proud to be an equal opportunity employer. We do not discriminate on the basis of race, religion, color, national origin, gender, gender identity, sexual orientation, age, marital status, disability, protected veteran status, or any other legally protected characteristics. At Turing we are dedicated to building a diverse, inclusive and authentic workplace and celebrate authenticity, so if you’re excited about this role but your past experience doesn’t align perfectly with every qualification in the job description, we encourage you to apply anyways. You may be just the right candidate for this or other roles.

For applicants from the European Union, please review Turing's GDPR notice here.