OpenAI· Safety Systems· San Francisco
Technical Lead, Safety Research
Comp$460K – $555K
Classified Tasks (14)
Automate 0%Augment 64%Human-Only 36%
Augment (9)
AI assists, human decides
Develop challenging evaluations to measure progress on safety, alignment, and robustness.
technical
Drive research on methods to improve safety-related common sense and generalizable reasoning.
technical
Design and implement evaluations to elicit or detect misalignment or inner goals of AI systems.
technical
Develop methods to support human oversight of long-running tasks.
technical
Actively evaluate the safety of models and systems through experiments, analyses, and testing.
analytical
Identify areas of risk in models and systems and propose concrete mitigation strategies.
analytical
Conduct state-of-the-art research on AI safety topics such as RLHF, adversarial training, and robustness.
technical
Implement new safety methods in OpenAI’s core model training pipelines.
technical
Launch and deploy safety improvements into OpenAI products.
operational
Human-Only (5)
Requires human judgment
Set north star goals and milestones for new research directions and track progress against those milestones.
leadership
Lead exploratory research projects to demonstrate feasibility and scalability of new safety approaches.
leadership
Define research directions and strategies to make AI systems safer, more aligned, and more robust.
leadership
Coordinate and collaborate with cross-functional teams (research, T&S, policy, alignment) to integrate safety requirements into development and deployment.
communication
Work horizontally across safety research and related teams to integrate different technical approaches for cohesive safety outcomes.
operational
Job description
Technical Lead, Safety Research | OpenAI Careers ## Technical Lead, Safety Research Safety Systems - San Francisco Apply now(opens in a new window) **About the Team** The Safety Systems team is responsible for various safety work to ensure our best models can be safely deployed to the real world to benefit the society and is at the forefront of OpenAI's mission to build and deploy safe AGI, driving our commitment to AI safety and fostering a culture of trust and transparency. The Safety Research team aims to fundamentally advance our capabilities for precisely implementing robust, safe behavior in AI models and systems. As capabilities continue to advance, it is imperative that our approaches to safety continue to improve and scale to address evolving risks. This is important both for ensuring our systems are robust to prevent harmful misuse as well as ensuring potential misalignment cannot cause harm. We are working on these problems in a way that is grounded in our current models and methods but that generalizes to future systems. We are growing our team to expand our research on methods that will improve safety for AGI and beyond. This will include exploratory research for example, new methods to improve safety common sense and generalizable reasoning, developing new evaluations to elicit or detect misalignment or inner goals of the AI, and new methods to support human oversight of long-running tasks. **About the Role** As a tech lead, you will be responsible for developing our strategy in new directions to address potential harms from misalignment or significant mistakes. This will in practice include: * Setting north star goals and milestones for new research directions, and developing challenging evaluations to track progress. * Personally driving or leading research in new exploratory directions to demonstrate feasibility and scalability of the approaches. * Working horizontally across safety research and related teams to ensure different technical approaches work together to achieve strong safety results. We’re looking for people who have a strong track record of practical research on safety and alignment, ideally in AI and LLMs, and have led large research efforts in the past. This role is based in San Francisco, CA. We use a hybrid work model of 3 days in the office per week and offer relocation assistance to new employees. **In this role, you will:** * Set the research directions and strategies to make our AI systems safer, more aligned and more robust. * Coordinate and collaborate with cross-functional teams, including the rest of the research organization, T&S, policy and related alignment teams, to ensure that our AI meets the highest safety standards. * Actively evaluate and understand the safety of our models and systems, identifying areas of risk and proposing mitigation strategies. * Conduct state-of-the-art research on AI safety topics such as RLHF, adversarial training, robustness, and more. * Implement new methods in OpenAI’s core model training and launch safety improvements in OpenAI’s products. **You might thrive in this role if you:** * Are excited about OpenAI’s mission of building safe, universally beneficial AGI and are aligned with OpenAI’s charter * Demonstrate a passion for AI safety and making cutting-edge AI models safer for real-world use. * Bring 4+ years of experience in the field of AI safety, especially in areas like RLHF, adversarial training, robustness, fairness & biases. * Hold a Ph.D. or other degree in computer science, machine learning, or a related field. * Possess experience in safety work for AI model deployment * Have an in-depth understanding of deep learning research and/or strong engineering skills. * Are a team player who enjoys collaborative work environments. **About OpenAI** OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of