Staff Software Engineer, GTM AI Engineering
$320k - $405k • Remote • Remote-Friendly (Travel-Required) | San Francisco, CA | Seattle, WA
Posted 1mo ago
Job Location
Remote-Friendly (Travel-Required) | San Francisco, CA | Seattle, WA
Tech Stack
Remote Work Policy
Fully remote
Categories
AI Agent Engineer
About the job
As a Staff Software Engineer on the GTM AI Engineering (Claudification) team, you will build the agents and AI systems that power Anthropic's go-to-market operations. You will advance existing agent capabilities to autonomously manage complete motions across sales areas like inbound, outbound, and pipeline management. Additionally, you will develop evaluation frameworks to ensure these agents are ready for customer-facing tasks and deliver tangible value. This senior role involves driving the technical direction for agents and evaluations within the team, owning projects from initial prototyping to production deployment, and collaborating with sellers, RevOps, and platform engineering partners. You will integrate full-stack engineering, including MCP servers and agentic systems, with hands-on evaluation work and contribute to architecting shared platforms for the go-to-market organization.
Responsibilities
- Build and operate autonomous agents for end-to-end go-to-market motions (inbound, outbound, pipeline management, customer engagement).
- Design human oversight mechanisms for each motion, including approval gates, handoffs, and escalation paths.
- Develop and execute evaluation frameworks for agent behavior in development and production.
- Instrument model and tool calls in production to measure agent actions' impact on pipeline and revenue.
- Ship MCP servers, agent skills, and web applications integrating with CRM, communication tools, and data warehouses.
- Set the technical direction for agent development, evaluation, and operation within the team.
- Architect shared codebases for the go-to-market organization, establishing conventions and review practices.
- Collaborate directly with sellers to ground agent designs in real-world workflows and iterate based on feedback.
- Identify repeatable patterns and provide insights to Anthropic's Product and Engineering teams.
- Maintain up-to-date knowledge of LLM capabilities, agent frameworks, and evaluation techniques.
Requirements
- Strong programming skills in Python or TypeScript with experience in production application development and operation.
- Production experience with LLMs, including context engineering, agent development, MCP development, tool use, and evaluation frameworks.
- Experience using evals and transcript analysis to identify and resolve issues in LLM systems.
- Working fluency with data, including SQL.
- Ability to navigate ambiguity and deliver solutions for complex problems.
- Passion for advancing safe, beneficial AI and user well-being.