Researcher, Alignment
At a glance
Mid-level AI Research role at OpenAI. San Francisco · full-time · $295,000–$500,000 base.
aimlroles summary, based on the employer's posting.
What you'll do
- Turn open questions about model behavior into hypotheses, evaluations or interventions, experiments, and evidence-based conclusions
- Create ways to assess context-sensitive alignment and measure whether models follow human intent and values
- Build evaluations and tools that test model robustness across different situations and quantify risks
- Study how alignment changes with compute, data, context and action length, and adversary resources
- Develop human-AI interaction approaches and oversight methods, and train models to judge correctness and risk
What you bring
- A PhD or equivalent research background in computer science, computational science, data science, cognitive science, or a related field
- Strong engineering ability to design and optimize large-scale machine learning systems, with PyTorch given as an example
- A solid grasp of alignment research, plus experience building data visualization or collection interfaces using TypeScript or Python
Who this fits
This role suits a researcher who can shape an ambiguous model-behavior problem into experiments and interpret what the evidence supports. The work is collaborative and hands-on, with both research engineering and research science paths. The role may be based in San Francisco or London, depending on team needs and location approval.
From the employer
About the Team
The Alignment team at OpenAI is dedicated to ensuring that our AI systems are safe, trustworthy, and consistently aligned with human values, even as they scale in complexity and capability. Our work is at the cutting edge of AI research, focusing on developing methodologies that enable AI to robustly follow human intent across a wide range of scenarios, including those that are adversarial or high-stakes. We concentrate on the most pressing challenges, ensuring our work addresses areas where AI could have the most significant consequences. By focusing on risks that we can quantify and where our efforts can make a tangible difference, we aim to ensure that our models are ready for the complex, real-world environments in which they will be deployed.
The two pillars of our approach are: (1) harnessing improved capabilities into alignment, making sure that our alignment techniques improve, rather than break, as capabilities grow, and (2) centering humans by developing mechanisms and interfaces that enable humans to both express their intent and to effectively supervise and control AIs, even in highly complex situations.
About the Role
As a Research Engineer / Research Scientist on the Alignment team, you will be at the forefront of ensuring that our AI systems consistently follow human intent, even in complex and unpredictable scenarios. Your role will involve designing and implementing scalable solutions that ensure the alignment of AI as their capabilities grow and that integrate human oversight into AI decision-making.
This role is especially well suited for someone who can move from an ambiguous model-behavior question to a concrete experimental setup: formulate the hypothesis, build the evaluation or intervention, run the experiment, analyze the result, and decide what the evidence supports. This role may be based in San Francisco or London, subject to team needs and location approval.
In this role, you will:
We are seeking research engineers and research scientists to help design and implement experiments for alignment research. Responsibilities may include:
Develop and evaluate alignment capabilities that are subjective, context-dependent, and hard to measure.
Design evaluations to reliably measure risks and alignment with human intent and values.
Build tools and evaluations to study and test model robustness in different situations.
Design experiments to understand laws for how alignment scales as a function of compute, data, lengths of context and action, as well as resources of adversaries.
Design and evaluate new Human-AI-interaction paradigms and scalable oversight methods that redefine how humans interact with, understand, and supervise our models.
Train model to be calibrated on correctness and risk.
Designing novel approaches for using AI in alignment research
You might thrive in this role if you:
Are a team player – willing to do a variety of tasks that move the team forward.
Have a PhD or equivalent experience in research in computer science, computational science, data science, cognitive science, or similar fields.
Have strong engineering skills, particularly in designing and optimizing large-scale machine learning systems(e.g., PyTorch).
Have a deep understanding of the science behind alignment algorithms and techniques.
Can develop data visualization or data collection interfaces (e.g., TypeScript, Python).
Enjoy fast-paced, collaborative, and cutting-edge research environments.
Want to focus on developing AI models that are trustworthy, safe, and reliable, especially in high-stakes scenarios.
About OpenAI
OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. We push the boundaries of the capabilities of AI systems and seek to safely deploy them to the world through our products. AI is an extremely powerful tool that must be created with safety and human needs at its core, and to achieve our mission, we must encompass and value the many different perspectives, voices, and experiences that form the full spectrum of humanity.
We are an equal opportunity employer, and we do not discriminate on the basis of race, religion, color, national origin, sex, sexual orientation, age, veteran status, disability, genetic information, or other applicable legally protected characteristic.
For additional information, please see OpenAI’s Affirmative Action and Equal Employment Opportunity Policy Statement.
Background checks for applicants will be administered in accordance with applicable law, and qualified applicants with arrest or conviction records will be considered for employment consistent with those laws, including the San Francisco Fair Chance Ordinance, the Los Angeles County Fair Chance Ordinance for Employers, and the California Fair Chance Act, for US-based candidates. For unincorporated Los Angeles County workers: we reasonably believe that criminal history may have a direct, adverse and negative relationship with the following job duties, potentially resulting in the withdrawal of a conditional offer of employment: protect computer hardware entrusted to you from theft, loss or damage; return all computer hardware in your possession (including the data contained therein) upon termination of employment or end of assignment; and maintain the confidentiality of proprietary, confidential, and non-public information. In addition, job duties require access to secure and protected information technology systems and related data security obligations.
To notify OpenAI that you believe this job posting is non-compliant, please submit a report through this form. No response will be provided to inquiries unrelated to job posting compliance.
We are committed to providing reasonable accommodations to applicants with disabilities, and requests can be made via this link.
OpenAI Global Applicant Privacy Policy
At OpenAI, we believe artificial intelligence has the potential to help people solve immense global challenges, and we want the upside of AI to be widely shared. Join us in shaping the future of technology.