Member of Technical Staff - Environments

About Patronus AI Patronus AI is a frontier lab developing simulation research and infrastructure to accelerate progress toward human-aligned AGI. We are on a mission to simulate all of the world’s intelligence. We are the team behind some of the earliest and most influential research in AI evaluation like FinanceBench , Lynx , SimpleSafetyTests , CopyrightCatcher , Humanity’s Last Exam , and more. We are formerly AI researchers and engineers from companies like Meta AI, Amazon AGI, and Google. Our customers include foundation model labs and Fortune 500 enterprises like Adobe. We are backed by top-tier investors like Lightspeed Venture Partners, Notable Capital, Stanford University, Noam Brown, Gokul Rajaram, and more. Responsibilities We’re looking for strong engineers - builders who can design and implement complex RL environments end-to-end. You’ll work at the intersection of research, systems engineering, and product, collaborating with infrastructure and research teams to create environments that test and steer model behavior at scale. You’ll be responsible for turning conceptual specifications into working environments with verifiable reward structures, automated verifiers, task generation pipelines, and reproducible simulations. These environments span from API- and web-based tasks to multi-agent simulations, structured reasoning challenges, and knowledge-work environments used by customers and researchers alike. In this role, you will: Design and implement RL environments that support large-scale agent evaluation and reinforcement learning experiments Build task generation pipelines, dynamic datasets, and scripted environments with controlled complexity and stochasticity Develop verifiers and reward models to automatically score trajectories and evaluate model reasoning Collaborate with infrastructure and systems engineers to ensure environments are scalable, reproducible, and instrumented for detailed telemetry Design APIs and orchestration frameworks for running, resetting, and evaluating agents across environments Partner with research and customer teams to translate open-ended specifications into verifiable, testable systems Optimize environment performance, logging, and reward reproducibility across distributed setups Qualifications "The number one qualification to succeed in this machine learning course is gumption” - John Lafferty, CS Professor at Yale Above all, we look for an eagerness to learn, passion for research, creativity in problem solving and a proactive mindset. You are a great fit if you have a background in the following: 3+ years experience in software engineering, simulation systems, or ML infrastructure Strong command of Python and systems-level programming Deep understanding of ML concepts. RL concepts are a plus - reward modeling, environment dynamics, verifiability, evaluation, and agent interaction loops Experience designing scalable data pipelines, browser or API simulations (e.g. Playwright, Selenium), or distributed compute frameworks Familiarity with instrumentation, metrics, and data pipelines for evaluation Proven ability to translate research or product goals into robust, maintainable systems Curiosity and conviction around building environments that steer AGI Benefits Competitive salary and equity packages Health, dental, and vision insurance plans 401(k) plan + matching In-office private chef Sponsored personal tax accounting Whoop band, Oura ring, Function Health Monthly meal stipend Monthly health and wellness stipend Equinox membership Fun global offsites! Patronus AI is an equal opportunity employer. We celebrate diversity in our workplace, and all qualified applicants will receive consideration for employment without regard to age, ancestry, color, family or medical care leave, gender identity or expression, genetic information, marital status, medical condition, national origin, physical or mental disability, political affiliation, protected v ... (truncated, view full listing at source)