DevOps / AgentOps Engineer, GTM Systems at Anthropic

Hybrid - San Francisco, CA

Apply
More jobs at Anthropic

Anthropic is hiring a DevOps / AgentOps Engineer for its GTM Systems team in San Francisco. The role focuses on building and maintaining an AI‑first CI/CD pipeline that supports Salesforce and custom internal applications, handling change classification, approval workflows, environment strategy, and audit compliance. The engineer will work closely with business analysts, software engineers, and integration engineers to accelerate production deployment while ensuring robust governance, observability, and compliance with SOX‑level controls. The position offers hybrid work, competitive compensation, equity donation matching, and a supportive office environment.

Salary

USD 320,000 - 405,000

Requirements

Skills

  • Built and run a CI/CD pipeline for a team, including branching model, merge gating, and rollback path
  • Hands‑on experience with Salesforce deployment mechanics (metadata API, source‑tracked development, org‑to‑org promotion) or comparable enterprise platform
  • Fluent use of AI coding tools and agentic workflows, with clear opinions on boundaries between agent and human work
  • Design for failure scenarios, including blast radius, sandboxing, permissions, and error handling
  • Comfortable working with GitHub Actions or comparable CI system, infrastructure‑as‑code, and scripting to glue platforms together
  • Ability to write clear design documents and defend them to engineers, business approvers, and auditors
  • Bachelor’s degree or equivalent combination of education, training, and/or experience

Responsibilities

  • Design, build, and operate the CI/CD pipeline for a production Salesforce org and a portfolio of custom internal applications, from branching and validation through deploy and rollback
  • Define how a change is classified and routed into an agentic, human‑in‑the‑loop, or AI‑assisted lane, specify gates for each lane, and manage escalation between lanes when validation fails or risk changes
  • Build the agent operations layer, defining scope, tools, permissions, sandboxing for Salesforce and custom‑app work, and restrictions on unsupervised actions
  • Implement approval workflows that keep PR review and business sign‑off as distinct gates with clear rules for change requirements, approvers, and evidence
  • Own environment strategy, secrets handling, deploy observability, and kill‑switch and rollback mechanics across all three lanes
  • Produce the audit trail and evidence required for a SOX‑scoped platform
  • Measure and report on pipeline metrics such as lead time, failure rate, lane distribution, and remaining manual work
  • Pair with engineers on the team, incorporate their feedback, and iteratively improve pipeline defaults

Technologies

SalesforceSalesforce metadata APISource‑tracked developmentOrg‑to‑org promotionAI coding toolsGitHub ActionsInfrastructure‑as‑codeScriptingSlackGearsetCopadosfdx‑based pipelines

Share job

See if your resume is ready for this job

See how our AI can optimize your resume and improve your chances for this role.