SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Turing is a research accelerator for frontier AI labs and enterprises deploying advanced AI systems. The company builds large-scale datasets and reinforcement learning (RL) environments that power post-training for leading AI labs and enterprises, creating RL environments to evaluate and improve models on complex, long-range workflows across high-value domains like Finance, Sales, Retail, Developer Tools, and Collaboration.
As Staff Research Engineer, you will own the end-to-end lifecycle of RL environment projects, spanning environment design, task generation, reward/verifier design, quality assurance, and delivery to frontier AI labs and enterprise clients. This is a hands-on technical leadership role where you directly influence revenue by being mapped to one or more AI labs and building RL environments tailored to their specific needs.
Key responsibilities include:
• End-to-End Ownership: Lead RL environment projects for one or more clients, ensuring environments match specifications, exceed quality expectations, and deliver on schedule.
• Data Quality: Ensure RL environments, input data, and generated data (agent trajectories, reward scores) meet frontier standards for realism, difficulty, and diversity.
• Team Building & Enablement: Work with operations counterparts to build teams of full-stack engineers, backend engineers, domain experts, QAs, data creators, and reviewers. You will interview, hire, onboard, train, and retain talent.
• Process Leadership: Establish processes for environment code generation, database schemas, seed data, task creation, and verifier design. Set up quality rubrics, automated validation scripts, and human-in-the-loop review processes.
• Customer Interaction: Own customer relationships for your RL environment projects, serving as primary contact for leading AI labs with regular updates, feedback collection, and scope/revenue growth identification.
• Sales & Solutioning: Participate in client solutioning conversations with sales teams; translate researcher needs into environment goals.
• Evals & Post-training: Demonstrate proof of value by running in-house RL fine-tuning experiments to measure model performance lifts or producing evaluation reports of frontier models on your environments.
Required qualifications include RL and post-training experience (RL fine-tuning, verifier/reward design, environment design), engineering management experience (leading teams, hiring, QA process setup), and systems thinking with database/API design capabilities.
