Research Engineer, Interpretability

About Anthropic Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems. About the role: You want to build and run elegant and thorough machine learning experiments to help us understand and steer the behavior of powerful AI systems. You care about making AI helpful, honest, and harmless, and are interested in the ways that this could be challenging in the context of human-level capabilities. You could describe yourself as both a scientist and an engineer. As a Research Engineer on Alignment Science, you'll contribute to exploratory experimental research on AI safety, with a focus on risks from powerful future systems (like those we would designate as ASL-3 or ASL-4 under our Responsible Scaling Policy ), often in collaboration with other teams including Interpretability, Fine-Tuning, and the Frontier Red Team. Our blog provides an overview of topics that the Alignment Science team is either currently exploring or has previously explored. Our current topics of focus include... Scalable Oversight: Developing techniques to keep highly capable models helpful and honest, even as they surpass human-level intelligence in various domains. AI Control: Creating methods to ensure advanced AI systems remain safe and harmless in unfamiliar or adversarial scenarios. Alignment Stress-testing : Creating model organisms of misalignment to improve our empirical understanding of how alignment failures might arise. Automated Alignment Research: Building and aligning a system that can speed up & improve alignment research. Alignment Assessments : Understanding and documenting the highest-stakes and most concerning emerging properties of models through pre-deployment alignment and

About Anthropic Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems. About the role: When you see what modern language models are capable of, do you wonder, "How do these things work? How can we trust them?" The Interpretability team at Anthropic is working to reverse-engineer how trained models work because we believe that a mechanistic understanding is the most robust way to make advanced systems safe. We’re looking for researchers and engineers to join our efforts. People mean many different things by "interpretability". We're focused on mechanistic interpretability, which aims to discover how neural network parameters map to meaningful algorithms. Some useful analogies might be to think of us as trying to do "biology" or "neuroscience" of neural networks using “microscopes” we build, or as treating neural networks as binary computer programs we're trying to "reverse engineer". A few places to learn more about our work and team at a high level are this introduction to Interpretability from our research lead, Chris Olah ; a discussion of our work on the Hard Fork podcast produced by the New York Times, and this blog post (and accompanying video) sharing more about some of the engineering challenges we’d had to solve to get these results. Some of our team's notable publications include A Mathematical Framework for Transformer Circuits , In-context Learning and Induction Heads , Toy Models of Superposition , Scaling Monosemanticity , and our Circuits’ Methods and Biology papers. This work builds on ideas from members' work prior to Anthropic such as the original circuits thread , Multimodal Neurons , Activation Atlases , and Building Blocks . We aim to create a solid foundation for mechanisticall

About Anthropic Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems. Note: we don't have open Research Manager positions on the Interpretability team at this time. However, we're actively growing our team of Research Engineers and Research Scientists . If you're excited about interpretability research and open to an individual contributor role, we encourage you to apply. About the Interpretability team When you see what modern language models are capable of, do you wonder, "How do these things work? How can we trust them?" The Interpretability team’s mission is to reverse engineer how trained models work, and Interpretability research is one of Anthropic’s core research bets on AI safety. We believe that a mechanistic understanding is the most robust way to make advanced systems safe. People mean many different things by "interpretability". We're focused on mechanistic interpretability, which aims to discover how neural network parameters map to meaningful algorithms. Some useful analogies might be to think of us as trying to do "biology" or "neuroscience" of neural networks, or as treating neural networks as binary computer programs we're trying to "reverse engineer". We aim to create a solid scientific foundation for mechanistically understanding neural networks and making them safe (see our vision post ). We have focused on resolving the issue of "superposition" (see Toy Models of Superposition , Superposition, Memorization, and Double Descent , and our May 2023 update ), which causes the computational units of the models, like neurons and attention heads, to be individually uninterpretable, and on finding ways to decompose models into more interpretable components. Our subsequent work which f

About the Team The Interpretability team studies internal representations of deep learning models. We are interested in using representations to understand model behavior, and in engineering models to have more understandable representations. We are particularly interested in applying our understanding to ensure the alignment of powerful AI systems. Our working style is collaborative and curiosity-driven. About the Role OpenAI is seeking a researcher passionate about understanding deep networks, with a strong background in engineering, quantitative reasoning, and the research process. You will develop and carry out a research plan in mechanistic interpretability, in close collaboration with a highly motivated team. You will play a critical role in helping OpenAI ensure future models remain safe even as they grow in capability. This will make a significant impact on our goal of building and deploying safe AGI. In this role, you will: Develop and publish research on techniques for understanding representations of deep networks. Engineer infrastructure for studying model internals at scale. Collaborate across teams to work on projects that OpenAI is uniquely suited to pursue. Guide research directions toward demonstrable usefulness and/or long-term scalability. You might thrive in this role if you: Are excited about OpenAI’s mission of ensuring AGI benefits all of humanity, and are aligned with OpenAI’s charter . Show enthusiasm for long-term AI safety & alignment, and have thought deeply about technical paths to safe AGI. Bring experience in the field of AI safety & alignment, mechanistic interpretability, or spiritually related disciplines. Hold a Ph.D. or have research experience in computer science, machine learning, or a related field. Thrive in environments involving large-scale AI systems, and are excited to make use of OpenAI’s unique resources in this area. Possess 2+ years of research engineering experience and proficiency in Python or similar languag

About the Team The Interpretability team studies internal representations of deep learning models. We are interested in using representations to understand model behavior, and in engineering models to have more understandable representations. We are particularly interested in applying our understanding to ensure the safety of powerful AI systems. Our working style is collaborative and curiosity-driven. About the Role OpenAI is seeking a researcher passionate about understanding deep networks, with a strong background in engineering, quantitative reasoning, and the research process. You will develop and carry out a research plan in mechanistic interpretability, in close collaboration with a highly motivated team. You will play a critical role in helping OpenAI ensure future models remain safe even as they grow in capability. This will make a significant impact on our goal of building and deploying safe AGI. In this role, you will: Develop and publish research on techniques for understanding representations of deep networks. Engineer infrastructure for studying model internals at scale. Collaborate across teams to work on projects that OpenAI is uniquely suited to pursue. Guide research directions toward demonstrable usefulness and/or long-term scalability. You might thrive in this role if you: Are excited about OpenAI’s mission of ensuring AGI benefits all of humanity, and are aligned with OpenAI’s charter . Show enthusiasm for long-term AI safety, and have thought deeply about technical paths to safe AGI. Bring experience in the field of AI safety, mechanistic interpretability, or spiritually related disciplines. Hold a Ph.D. or have research experience in computer science, machine learning, or a related field. Thrive in environments involving large-scale AI systems, and are excited to make use of OpenAI’s unique resources in this area. Possess 2+ years of research engineering experience and proficiency in Python or similar languages. Are deeply curious. About OpenA

About Decagon Decagon is the leading conversational AI platform empowering every brand to deliver concierge customer experiences. Our technology enables industry-defining enterprises like Avis Budget Group, Block’s Cash App and Square, Chime, Oura Health, and Hunter Douglas to deploy AI agents that power personalized, deeply satisfying interactions across voice, chat, email, SMS, and every other channel. We’re building a future where customer experiences are being redefined from support tickets and hold music to faster resolutions, richer conversations, and deeper relationships. We’re proud to be backed by world-class investors who share that vision, including a16z, Accel, Bain Capital Ventures, Coatue, and Index Ventures, along with many others. We’re an in-office company, driven by a shared commitment to excellence and velocity. Our values — Just Get It Done, Invent What Customers Want, Winner’s Mindset, and The Polymath Principle — shape how we work and grow as a team. About the Team Read more about the research team's work here: https://decagon.ai/blog/introducing-decagon-labs The Research team develops the model and decision-making stack that powers Decagon’s conversational agents for enterprise support. We research, adapt, and implement state-of-the-art techniques in model training, prompting, orchestration, and evaluation in order to make our agents more accurate, robust, and efficient in real-world deployments. Our goal is to push the frontier of applied conversational AI: agents that reliably understand nuanced intent, track long context, and take the right actions under uncertainty. We measure success the way customers feel it: higher resolution rates, better user satisfaction, and consistent behavior at scale. About the Role As a Research Engineer, you’ll be responsible for building industry-leading conversational AI models that power Decagon’s agent, and taking them all the way from idea to production. You’ll own multi-quarter initiatives that push the a