Research Engineer / Scientist, Tool Use Safety at ANTHROPIC PBC DBA ANTHROPIC INC

, , -

Full Time

Start Date

Immediate

Expiry Date

25 Dec, 25

Salary

425000.0

Posted On

26 Sep, 25

Experience

2 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Yes

Skills

Machine Learning, Reinforcement Learning, Tool Use Safety, Software Engineering, Collaboration, Research, Evaluation, Programming, Communication, Problem-Solving

Industry

Research Services

Description

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 team The Tool Use Team within Research is responsible for making Claude the world's most capable, safe, reliable, and efficient model for tool use and agentic applications. The team focuses on the foundational layer - solving core problems such as tool use safety (e.g. prompt injection robustness), tool call accuracy, long horizon & complex tool use workflow, large scale & dynamic tools, and tool use efficiency. These are foundations to the majority of Anthropic’s customers as well as internal teams building specific agentic applications such as Claude for Chrome, Computer Use, Claude Code, Search. About the role We're looking for Research Engineers/Scientists to help us advance the frontier of safe tool use. With tool use adoption accelerating rapidly across our platform, the next generation requires even more breakthrough research to enable us to scale responsibly: for example, training Claude to be extremely robust against sophisticated prompt injection, preventing data exfiltration attempts through tool misuse, defending against adversarial attacks in realistic multi-turn agent conversations, and ensuring safety when agents operate autonomously for longer horizons with access to a large number of tools. You'll collaborate with a diverse group of researchers and engineers to advance safe tool use in Claude. You'll own the full research lifecycle—from identifying fundamental limitations to implementing solutions that ship in production models. This work is critical for derisking our model’s increasing capabilities and empowering Claude to more autonomously assist users. Note: For this role, we conduct all interviews in Python. Responsibilities: Design and implement novel and scalable reinforcement learning methodologies that push the state of the art of tool use safety Define and pursue research agendas that push the boundaries of what's possible Build rigorous, realistic evaluations that capture the complexity of real-world tool use safety challenges Ship research advances that directly impact and protect millions of users Collaborate with other safety research (e.g. Safeguards, Alignment Science), capabilities research, and product teams to drive fundamental breakthroughs in safety, and work with teams to ship these into production Design, implement, and debug code across our research and production ML stacks Contribute to our collaborative research culture through pair programming, technical discussions, and team problem-solving You may be a good fit if you: Passionate about our safety mission Are driven by real-world impact and excited to see research ship in production Have strong machine learning research/applied-research experience, or a strong quantitative background such as physics, mathematics, or quantitative finance research Write clean, reliable code and have solid software engineering skills Communicate complex ideas clearly to diverse audiences Are hungry to learn and grow, regardless of years of experience Strong candidates may also have one or more of the following: Experience with tool use/agentic safety, trust & safety, or security Experience with reinforcement learning techniques and environments Experience with language model training, fine-tuning or evaluation Experience building AI agents or autonomous systems Published influential work in relevant ML areas, especially around LLM safety & alignment Deep expertise in a specialized area (e.g., RL, security, or mathematical foundations), even if still developing breadth in adjacent areas Experience shipping features or working closely with product teams Enthusiasm for pair programming and collaborative research The expected salary range for this position is: Annual Salary: $315,000—$425,000 USD Logistics Education requirements: We require at least a Bachelor's degree in a related field or equivalent experience. Location-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices. Visa sponsorship: We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this. We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed. Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you're interested in this work. We think AI systems like the ones we're building have enormous social and ethical implications. We think this makes representation even more important, and we strive to include a range of diverse perspectives on our team. 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. Come work with us! Anthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space in which to collaborate with colleagues. Guidance on Candidates' AI Usage: Learn about our policy for using AI in our application process

How To Apply:

Incase you would like to apply to this job directly from the source, please click here

Responsibilities

Design and implement novel reinforcement learning methodologies to enhance tool use safety. Collaborate with researchers and engineers to advance safe tool use and ship research advances into production models.