Principal Research Engineer - RL Gyms

About Turing

Based in San Francisco, California, Turing is the world’s leading research accelerator for frontier AI labs and a trusted partner for global enterprises looking to deploy advanced AI systems. Turing accelerates frontier research with high-quality data, specialized talent, and training pipelines that advance thinking, reasoning, coding, multimodality, and STEM. For enterprises, Turing builds proprietary intelligence systems that integrate AI into mission-critical workflows, unlock transformative outcomes, and drive lasting competitive advantage.

Recognized by Forbes, The Information, and Fast Company among the world’s top innovators, Turing’s leadership team includes AI technologists from Meta, Google, Microsoft, Apple, Amazon, McKinsey, Bain, Stanford, Caltech, and MIT. Learn more at

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 Deep Mind, Microsoft AI, Amazon, Apple, and many more. We create RL environments to evaluate and improve our customers' models on complex, long-range, multi-step workflows across high-GDP-value domains such as Finance, Sales, Retail, Developer Tools, Collaboration, Customer Experience.

The environments vary depending on the model capability being evaluated / improved, a few examples of environment types are listed here:

We are looking for a Frontier Data Lead – RL to own the end-to-end lifecycle of RL environment projects, spanning environment design, task generation, reward/verifier design, quality, and delivery to frontier AI labs and enterprise clients.

This is a hands-on technical leadership role where you influence revenue directly – you will be mapped to one or more AI labs and build RL environments specific to their needs. You will lead teams of engineers, subject matter experts (e.g. Finance expert, if you’re building an RL environment for investment banking workflows), researchers, and data ops teammates to achieve this.

• End-to-End Ownership: Lead RL Environment projects end-to-end for one or more clients, ensuring the environment you and your team create matches the client’s spec, surpasses quality expectations, and is delivered on time.
• Data Quality: Ensure the RL environments you produce, the data that goes into those environments, and the the data generated from them (e.g. agent trajectories and reward scores) meet frontier standards for realism, difficulty, diversity.
• Team building and enablement: Work with your Ops counterparts to build the team of full-stack engineers, back-end engineers, domain experts, QAs, data creators, reviewers, and others you’ll need to deliver the environment on time. You’ll interview, hire, onboard, train, retain talent for your team
• Process Leadership: Set the process that each of the above team members follows to generate environment code, database schemas, seed data, tasks, and verifiers; set up quality rubrics, automated validation scripts, and human-in-the-loop review processes for every aspect of the environment and data for the environment.
• Customer Interaction: Own customer relationships for your RL Environment project(s), and act as the primary point of contact for leading AI labs, providing regular updates, asking for feedback, and identifying opportunities to grow project scope and revenue.
• Sales & Solutioning: participate in client solutioning conversations alongside our sales teammates; understand the needs of researchers at AI labs, translate those needs into environment goals
• Evals & Post-training: Demonstrate proof of value for your environments by running inhouse RL fine tuning experiments to measure model performance lifts on agent trajectories; or by producing eval reports of frontier models on your environment and tasks

• RL & Post-training experience: familiarity with RL fine tuning,…