Software Engineer, Agents Infrastructure

About the team: The Agents Infrastructure team at Anthropic is on a mission to build seamless and robust infrastructure and SDKs for LLM-based agents. Our current priorities include developing sandboxed code execution environments and associated tool use SDKs.



About Anthropic: Anthropic is an AI safety and research company working to build reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our customers and society as a whole. Our interdisciplinary team has experience across ML, physics, policy, business, and product.

Responsibilities: Design and implement secure, scalable sandboxed execution environments for AI agents using containerization technologies Create intuitive and flexible SDKs for tool use and function calling in LLM-based agents Collaborate closely with researchers to onboard research ideas onto the platform You may be a good fit if you: 8+ years of industry-related experience Have a strong software engineering background and are interested in working closely with researchers and other engineers Enjoy pair programming (we love to pair!) Care about code quality, testing, and performance Are passionate about the potential impact of AI and are committed to developing safe and beneficial systems Strong candidates may also have: 8+ years of experience in software engineering, with a focus on systems programming or large-scale distributed systems Strong knowledge of containerization technologies Experience building scalable, serverless platforms Building security-oriented infrastructure Familiarity with LLM agent frameworks (e.g., Langchain) Deadline to apply: None. Applications will be reviewed on a rolling basis.


#J-18808-Ljbffr