AI Platform Engineer Anthropic US

Responsibilities

• Design, build, deploy, and maintain reusable platform capabilities and reference architectures for secure enterprise AI, machine learning, LLM, RAG, and agentic applications.
• Create secure integrations with the Anthropic API, Claude models, enterprise data, APIs, workflow systems, and authorized tools using standardized authentication, context, structured-output, logging, and rate-limit patterns.
• Establish CI/CD, versioning, testing, release, rollback, evaluation, monitoring, and lifecycle-management practices for AI applications, prompts, models, infrastructure, and integrations.
• Design and manage cloud infrastructure, infrastructure-as-code, containerized deployments, identity and access controls, security controls, logging, auditing, disaster recovery, and business continuity.
• Build data-ingestion, transformation, indexing, retrieval, RAG, vector-search, and enterprise data-access patterns with appropriate data quality, lineage, permissions, retention, and governance.
• Implement AI observability, tracing, safeguards, output validation, source attribution, confidence thresholds, fallback behavior, approval gates, and human-in-the-loop workflows.
• Build and maintain integrations among AI platforms, ServiceNow, identity providers, enterprise APIs, workflow tools, collaboration platforms, and line-of-business systems.
• Provide technical guidance, participate in architecture reviews and customer workshops, troubleshoot client integrations, and convert recurring requirements into reusable platform features and accelerators.

Requirements

• 5+ years of experience in platform engineering, cloud engineering, DevOps, software engineering, data engineering, systems integration, or related technical roles.
• Hands-on experience designing and deploying cloud-native applications and services on AWS, Microsoft Azure, and/or Google Cloud Platform.
• Strong experience with CI/CD, Git-based workflows, automated testing, infrastructure as code, and production release processes.
• Experience with Docker, Kubernetes, serverless services, or comparable cloud-native platforms.
• Proficiency in Python, JavaScript/TypeScript, Java, Go, Bash, or similar programming and scripting languages.
• Experience designing and consuming REST APIs, integrating enterprise applications, and implementing authentication and authorization patterns.
• Hands-on experience with LLM-powered applications, generative AI services, AI/ML platforms, RAG systems, AI workflow automation, or related technologies.
• Familiarity with prompt and context engineering, token management, embeddings, vector search, RAG, structured outputs, tool use/function calling, evaluations, and model monitoring.
• Experience with logging, metrics, tracing, alerting, observability, and incident management.
• Strong knowledge of cloud security, identity and access management, secrets management, network security, and secure software-development practices.
• Experience with relational databases, NoSQL databases, data warehouses, object storage, search platforms, or vector databases.
• Strong problem-solving, troubleshooting, communication, and documentation skills, with the ability to work in a collaborative, customer-oriented environment.
• Preferred qualifications include Claude, Anthropic API, Anthropic Console, Claude Code, Model Context Protocol, LLM frameworks, MLOps platforms, vector databases, cloud and Kubernetes tooling, FinOps, ServiceNow, consulting, professional services, enterprise architecture, or client-facing technical delivery experience.
• Relevant certifications in cloud platforms, Kubernetes, DevOps, security, data engineering, ServiceNow, AI/ML, or Anthropic technologies are a plus.

Benefits

• The posting describes a diverse and inclusive workplace, equal opportunity and affirmative action employment, and disability accommodation support.
• Travel is based on client and business needs, and the listed location arrangement is described as location/hybrid/remote.