Applied Safety Research Engineer, Safeguards
San Francisco, CAFull-TimeMid-levelSoftware Engineering
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
- We are looking for a research-oriented engineer to develop the methods that make our safety evaluations representative, robust, and informative. You'll work on questions like: How do we measure whether a model is safe? How do we create evaluations that reflect real-world usage rather than synthetic benchmarks? How do we know our graders are accurate?
- This role sits at the intersection of applied ML research and engineering. You'll design experiments to improve how we evaluate model behavior, then ship those methods into pipelines that inform model training and deployment decisions. Your work will directly shape how Anthropic understands and improves the safety of our models across misuse, prompt injection, and user well-being.
Responsibilities
- Design and run experiments to improve evaluation quality—developing methods to generate representative test data, simulate realistic user behavior, and validate grading accuracy
- Research how different factors (multi-turn conversations, tools, long context, user diversity) impact model safety behavior
- Analyze evaluation coverage to identify gaps and inform where we need better measurement
- Productionize successful research into evaluation pipelines that run during model training, launch and beyond.
- Collaborate with Policy and Enforcement to translate real-world harm patterns into measurable evaluations
- Build tooling that enables policy experts to create and iterate on evaluations
- Surface findings to research and training teams to drive upstream model improvements
- Design and run experiments to improve evaluation quality—developing methods to generate representative test data, simulate realistic user behavior, and validate grading accuracy
- Research how different factors (multi-turn conversations, tools, long context, user diversity) impact model safety behavior
- Analyze evaluation coverage to identify gaps and inform where we need better measurement
- Productionize successful research into evaluation pipelines that run during model training, launch and beyond.
- Collaborate with Policy and Enforcement to translate real-world harm patterns into measurable evaluations
- Build tooling that enables policy experts to create and iterate on evaluations
- Surface findings to research and training teams to drive upstream model improvements
You may be a good fit if you
- Have 4+ years of software engineering or ML engineering experience
- Are proficient in Python and comfortable working across the stack
- Have experience building and maintaining data pipelines
- Are comfortable with data analysis and can draw insights from large datasets
- Have experience with LLMs and understand their capabilities and failure modes
- Can move fluidly between prototyping and production-quality code
- Are excited by ambiguous problems and can translate them into concrete experiments
- Care deeply about AI safety and want your work to have real impact
- Have 4+ years of software engineering or ML engineering experience
- Are proficient in Python and comfortable working across the stack
- Have experience building and maintaining data pipelines
- Are comfortable with data analysis and can draw insights from large datasets
- Have experience with LLMs and understand their capabilities and failure modes
- Can move fluidly between prototyping and production-quality code
- Are excited by ambiguous problems and can translate them into concrete experiments
- Care deeply about AI safety and want your work to have real impact
Strong candidates may also have experience with
- Red teaming, adversarial testing, or jailbreak research on AI systems
- Building or contributing to LLM evaluation frameworks or benchmarks
- Trust and safety, content moderation, or abuse detection systems
- Synthetic data generation or data augmentation
- Distributed systems or large-scale data processing
- Prompt engineering or LLM application development
- Red teaming, adversarial testing, or jailbreak research on AI systems
- Building or contributing to LLM evaluation frameworks or benchmarks
- Trust and safety, content moderation, or abuse detection systems
- Synthetic data generation or data augmentation
- Distributed systems or large-scale data processing
- Prompt engineering or LLM application development
- 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.
