[Expression of Interest] Research Scientist/Engineer, Honesty
New York City, NY; San Francisco, CAFull-TimeMid-levelResearch
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:
- As a Research Scientist/Engineer focused on honesty within the Finetuning Alignment team, you'll spearhead the development of techniques to minimize hallucinations and enhance truthfulness in language models. Your work will focus on creating robust systems that are accurate and reflect their true levels of confidence across all domains, and that work to avoid being deceptive or misleading. Your work will be critical for ensuring our models maintain high standards of accuracy and honesty across diverse domains.
- Note: The team is based in New York and so we have a preference for candidates who can be based in New York. For this role, we conduct all interviews in Python. We have filled our headcount for 2025. However, we are leaving this form open as an expression of interest since we expect to be growing the team in the future, and we will review your application when we do. As such, you may not hear back on your application to this team until the new year
Responsibilities
- Design and implement novel data curation pipelines to identify, verify, and filter training data for accuracy given the model’s knowledge
- Develop specialized classifiers to detect potential hallucinations or miscalibrated claims made by the model
- Create and maintain comprehensive honesty benchmarks and evaluation frameworks
- Implement techniques to ground model outputs in verified information, such as search and retrieval-augmented generation (RAG) systems
- Design and deploy human feedback collection specifically for identifying and correcting miscalibrated responses
- Design and implement prompting pipelines to generate data that improves model accuracy and honesty
- Develop and test novel RL environments that reward truthful outputs and penalize fabricated claims
- Create tools to help human evaluators efficiently assess model outputs for accuracy
You may be a good fit if you
- Have an MS/PhD in Computer Science, ML, or related field
- Possess strong programming skills in Python
- Have industry experience with language model finetuning and classifier training
- Show proficiency in experimental design and statistical analysis for measuring improvements in calibration and accuracy
- Care about AI safety and the accuracy and honesty of both current and future AI systems
- Have experience in data science or the creation and curation of datasets for finetuning LLMs
- An understanding of various metrics of uncertainty, calibration, and truthfulness in model outputs
Strong candidates may also have
- Published work on hallucination prevention, factual grounding, or knowledge integration in language models
- Experience with fact-grounding techniques
- Background in developing confidence estimation or calibration methods for ML models
- A track record of creating and maintaining factual knowledge bases
- Familiarity with RLHF specifically applied to improving model truthfulness
- Worked with crowd-sourcing platforms and human feedback collection systems
- Experience developing evaluations of model accuracy or hallucinations
- Join us in our mission to ensure advanced AI systems behave reliably and ethically while staying aligned with human values.
- The annual compensation range for this role is listed below.
- For sales roles, the range provided is the role’s On Target Earnings ("OTE") range, meaning that the range includes both the sales commissions/sales bonuses target and annual base salary for the role.
How we're different
- We believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact — advancing our long-term goals of steerable, trustworthy AI — rather than work on smaller and more specific puzzles. We view AI research as an empirical science, which has as much in common with physics and biology as with traditional efforts in computer science. We're an extremely collaborative group, and we host frequent research discussions to ensure that we are pursuing the highest-impact work at any given time. As such, we greatly value communication skills.
- The easiest way to understand our research directions is to read our recent research. This research continues many of the directions our team worked on prior to Anthropic, including: GPT-3, Circuit-Based Interpretability, Multimodal Neurons, Scaling Laws, AI & Compute, Concrete Problems in AI Safety, and Learning from Human Preferences.
