Anthropic, Claude & LLM Platform Enablement

• Build and maintain secure, reusable integrations with the Anthropic API, Claude models, and other approved AI services.
• Enable LLM-powered applications through standardized patterns for authentication, model access, prompt and context management, structured outputs, tool use, logging, error handling, and rate-limit management.
• Support Claude-based enterprise use cases involving document analysis, knowledge assistance, workflow automation, agentic task execution, summarization, classification, and decision support.
• Develop technical patterns for long-context workflows, document processing, RAG, structured data extraction, and model-driven automation.
• Support secure Model Context Protocol (MCP) and comparable tool-integration patterns that allow AI applications to access approved enterprise systems and data safely.
• Stay current on Anthropic platform capabilities, product releases, security guidance, technical enablement, and responsible AI practices.
• Complete relevant Anthropic partner training and enablement as available and help translate learning into reusable NewRocket engineering standards.

LLMOps, MLOps & AI Operations

• Establish and operate CI/CD pipelines for AI applications, model configurations, prompts, evaluation assets, infrastructure, and integration services.
• Implement versioning, testing, release-management, rollback, and change-control practices for AI solutions.
• Build and maintain LLMOps and MLOps capabilities, including model/prompt configuration management, evaluation pipelines, deployment automation, monitoring, and lifecycle management.
• Develop automated evaluation and regression-testing frameworks to measure AI quality before and after releases.
• Support production operations for AI services, including incident response, troubleshooting, root-cause analysis, capacity planning, and service-level monitoring.
• Define and monitor operational metrics such as availability, latency, throughput, token consumption, model cost, tool-call success rates, task-completion rates, and error rates.
• Improve platform reliability, performance, resilience, and cost efficiency through automation, tuning, and operational improvements.

Cloud Infrastructure, DevOps & Security

• Design and manage cloud infrastructure across AWS, Microsoft Azure, Google Cloud Platform, or client-approved environments.
• Build and maintain infrastructure using infrastructure-as-code tools such as Terraform, CloudFormation, Bicep, Pulumi, or comparable technologies.
• Implement containerized application and AI-service deployments using Docker, Kubernetes, serverless services, and cloud-native application patterns.
• Develop secure CI/CD workflows using Git-based source control, automated testing, artifact management, secrets management, and policy controls.
• Implement identity, access, and authentication patterns, including role-based access control, least-privilege access, API security, service accounts, and credential rotation.
• Partner with security, compliance, and client teams to ensure AI platforms align with enterprise security, privacy, regulatory, and data-residency requirements.
• Implement logging, monitoring, auditing, vulnerability management, disaster-recovery, and business-continuity practices for production AI services.

Data Platform & RAG Enablement

• Build and support secure data-ingestion, transformation, indexing, and retrieval pipelines for enterprise AI applications.
• Design platform patterns for RAG, including document ingestion, parsing, chunking, metadata enrichment, embeddings, vector stores, hybrid search, retrieval, reranking, and source attribution.
• Integrate AI applications with structured and unstructured enterprise data sources, including databases, data warehouses, document repositories, knowledge bases, ServiceNow, and third-party SaaS platforms.
• Work with data engineers to establish data-quality, lineage, cataloging, permissions, retention, and governance practices that support trustworthy AI.
• Enable appropriate data-access controls so AI solutions retrieve and process only data the requesting user or service is authorized to access.
• Support data platforms and technologies such as Snowflake, Databricks, PostgreSQL, MongoDB, Elasticsearch/OpenSearch, vector databases, and cloud storage services, as appropriate.

Responsible AI, Governance & Observability

• Implement technical controls that support responsible, secure, and governable AI deployments.
• Build safeguards for sensitive-data handling, data masking, content filtering, prompt injection, unsafe tool use, unauthorized access, and unintended agent behavior.
• Enable grounding, output validation, source attribution, confidence thresholds, fallback behavior, approval gates, and human-in-the-loop workflows.
• Implement AI observability and tracing across prompts, model calls, retrieval pipelines, tool execution, workflow outcomes, latency, errors, costs, and user feedback.
• Partner with AI Architects and governance stakeholders to document platform standards, risk controls, operating procedures, and solution limitations.
• Support auditability and compliance requirements through appropriate logging, retention, access reviews, and operational documentation.

Enterprise Integration & ServiceNow Enablement

• Build and maintain integration patterns between AI platforms, ServiceNow, enterprise APIs, identity providers, workflow tools, collaboration platforms, and line-of-business systems.
• Support technical enablement for ServiceNow AI and workflow experiences, including IntegrationHub, Flow Designer, Virtual Agent, Now Assist, AI Agents, APIs, and knowledge-management capabilities where applicable.
• Develop secure APIs, middleware services, event-driven integrations, and automation components that support AI-enabled workflows.
• Collaborate with Forward Deployed AI Engineers to troubleshoot complex client integrations and transition successful engagement solutions into reusable platform components.

Collaboration & Technical Leadership

• Work closely with AI Architects, AI/ML Engineers, Data Engineers, Product Engineering, ServiceNow developers, Business Process Consultants, and client technology teams.
• Provide technical guidance on AI platform engineering, cloud architecture, DevOps, LLMOps, data integration, performance, and security best practices.
• Contribute to internal playbooks, runbooks, reference architectures, technical documentation, reusable modules, and knowledge-sharing sessions.
• Identify recurring client requirements and convert them into scalable, productized platform features and accelerators.
• Participate in technical discovery, architecture reviews, demos, implementation planning, and customer workshops as needed.

What Success Looks Like in the First 6 Months

• Establish or enhance reusable, secure deployment patterns for Claude-powered and other enterprise AI applications.
• Deliver reliable cloud, integration, data, and observability capabilities that support multiple AI Foundry client engagements.
• Implement CI/CD, infrastructure-as-code, monitoring, and LLMOps practices that improve deployment speed, quality,