Principal Research Engineer - RL Gyms

About Turing

Turing is based in San Francisco, California. It is a research accelerator for frontier AI labs and a trusted partner for global enterprises deploying advanced AI systems. Turing accelerates frontier research with high-quality data, specialized talent, and training pipelines. For enterprises, Turing builds proprietary intelligence systems integrating AI into critical workflows, driving competitive advantage. Turing’s leadership includes AI technologists from Meta, Google, Microsoft, Apple, Amazon, McKinsey, Bain, Stanford, and MIT. Learn more at www.turing.com.

The Role

We are seeking a Principal Research Engineer – RL to lead the end-to-end lifecycle of RL environment projects. This role involves influencing revenue directly by mapping to AI labs and building RL environments tailored to their needs. Key responsibilities include:

• End-to-End Ownership: Lead RL Environment projects for one or more clients, ensuring alignment with client specifications, quality, and timely delivery.
• Data Quality: Ensure the realism, difficulty, and diversity of the RL environments and data generated.
• Team Building & Enablement: Build and manage teams of engineers, subject matter experts, researchers, and data ops teammates.
• Process Leadership: Establish processes for environment code, database schemas, seed data, tasks, and verifiers; set up quality rubrics and validation scripts.
• Customer Interaction: Manage client relationships, provide regular updates, gather feedback, and identify growth opportunities.
• Sales & Solutioning: Participate in client solutioning conversations, translating researcher needs into environment goals.
• Evals & Post-training: Demonstrate proof of value through RL fine-tuning experiments or eval reports of frontier models on your environment and tasks.

Who We're Looking For

• RL & Post-training experience: Familiarity with RL fine tuning, reward design, and/or environment design.
• Engineering Management experience: Leadership of engineering teams, including hiring and setting up QA processes.
• Systems thinking & Database/API design: Ability to simulate data schema and API interfaces.
• Hands-on technical capability: Willingness to write code, Python and SQL experience preferred.
• Operational leadership: Experience managing complex data pipelines, multi-stakeholder delivery, and concurrent high-stakes projects.
• Cross-functional communication: Ability to communicate with researchers, domain experts, and diverse teams.
• Background in Computer Science, Machine Learning, or related field.

Why Turing

• Work directly with leading AI labs and enterprises in RL environment design and post-training.
• Real impact: Your environments will be used to evaluate and train frontier models on GDP-moving tasks.
• Talent-dense team with high autonomy, rapid iteration, and rapid learning curve.
• Competitive compensation and flexible working hours.
• Amazing work culture, diverse and inclusive team, and supportive environment.
• Advantages of joining Turing: Client-first approach, start-up speed, and Al-forward mindset.